Not in the top 1,000 by GitHub stars
haabe/mycelium
Prevent wasting time building the wrong thing. A plugin that keeps you and your AI coding agent focused, from first idea to market.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/mycelium/skills/a11y-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/adopt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/assumption-test/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/bias-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/bvssh-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/canvas-health/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/canvas-sync/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/canvas-update/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/corrections-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/count/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/cycle-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/cynefin-classify/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/define-done/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/definition-of-done/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/delivery-bootstrap/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/devils-advocate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/diamond-assess/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/diamond-progress/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/diamond-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/dora-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/eval-runner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/fan-out/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/feedback-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/framework-health/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/friction-log/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/gist-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/handoff/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/harms-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/ice-score/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/interview/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/jtbd-map/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/launch-tier/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/log-evidence/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/metrics-detect/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/metrics-pull/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/migrate-from-legacy/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/mocked-persona-interview/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/ost-builder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/ost-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/ping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/preflight/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/privacy-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/prompt-optimizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/purpose-properties/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/receipt-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/reflexion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/regulatory-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/retrospective/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/scaffold-cost-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/security-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/service-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/setup/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/start/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/team-shape/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/theory-fidelity/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/threat-model/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/usability-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/user-interview/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/user-needs-map/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/wardley-map/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/wiring-contract/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
plugins/mycelium/skills/xai-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_15/compliant/plugins/mycelium/skills/interview/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_15/heuristic_candidate/plugins/mycelium/skills/new_user_intake/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_15/missing_wrapping/plugins/mycelium/skills/interview/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_31/missing_preflight/plugins/mycelium/skills/badskill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_31/present/plugins/mycelium/skills/goodskill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_41/missing_preamble/plugins/mycelium/skills/diamond-assess/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_41/with_preamble/plugins/mycelium/skills/diamond-assess/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_42/missing_preamble/plugins/mycelium/skills/dora-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_42/with_preamble/plugins/mycelium/skills/dora-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_43/invalid_value/plugins/mycelium/skills/ost-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_43/missing_body/plugins/mycelium/skills/ost-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_43/missing_frontmatter/plugins/mycelium/skills/ost-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_43/valid_none/plugins/mycelium/skills/ost-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_43/valid_yes/plugins/mycelium/skills/ost-render/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_45/compliant/plugins/mycelium/skills/bvssh-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_45/compliant/plugins/mycelium/skills/ice-score/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_45/missing_marker/plugins/mycelium/skills/bvssh-check/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_45/missing_marker/plugins/mycelium/skills/ice-score/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_5/all_present/plugins/mycelium/skills/canvas-update/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_5/missing_canvas_in_mapping/plugins/mycelium/skills/canvas-update/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_8/missing_name/plugins/mycelium/skills/bad_skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
tests/bash/fixtures/check_8/valid/plugins/mycelium/skills/good_skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
ac08e7875ed5 → d44421b0667b
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → ac08e7875ed5
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit d44421b0667bb71ad515ae7576dfc0f47b00504f
git clone --filter=blob:none --no-checkout https://github.com/haabe/mycelium.git .hotskills/haabe-mycelium && git -C .hotskills/haabe-mycelium checkout --detach d44421b0667bb71ad515ae7576dfc0f47b00504f
# Copy each selected skill directory from .hotskills/haabe-mycelium into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/haabe/mycelium.git .hotskills/haabe-mycelium && git -C .hotskills/haabe-mycelium checkout --detach d44421b0667bb71ad515ae7576dfc0f47b00504f
# Copy each selected skill directory from .hotskills/haabe-mycelium into .agents/skills/<skill-name>/51GitHub stars
1star in 7 days
85skills in this repository
55commits in 30 days
Heat
3.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- a11y-check
plugins/mycelium/skills/a11y-check - adopt
plugins/mycelium/skills/adopt - assumption-test
plugins/mycelium/skills/assumption-test - bias-check
plugins/mycelium/skills/bias-check - bvssh-check
plugins/mycelium/skills/bvssh-check - canvas-health
plugins/mycelium/skills/canvas-health - canvas-sync
plugins/mycelium/skills/canvas-sync - canvas-update
plugins/mycelium/skills/canvas-update - corrections-audit
plugins/mycelium/skills/corrections-audit - count
plugins/mycelium/skills/count - cycle-render
plugins/mycelium/skills/cycle-render - cynefin-classify
plugins/mycelium/skills/cynefin-classify - define-done
plugins/mycelium/skills/define-done - definition-of-done
plugins/mycelium/skills/definition-of-done - delivery-bootstrap
plugins/mycelium/skills/delivery-bootstrap - devils-advocate
plugins/mycelium/skills/devils-advocate - diamond-assess
plugins/mycelium/skills/diamond-assess - diamond-progress
plugins/mycelium/skills/diamond-progress - diamond-render
plugins/mycelium/skills/diamond-render - dora-check
plugins/mycelium/skills/dora-check - eval-runner
plugins/mycelium/skills/eval-runner - fan-out
plugins/mycelium/skills/fan-out - feedback-review
plugins/mycelium/skills/feedback-review - framework-health
plugins/mycelium/skills/framework-health - friction-log
plugins/mycelium/skills/friction-log - gist-plan
plugins/mycelium/skills/gist-plan - handoff
plugins/mycelium/skills/handoff - harms-check
plugins/mycelium/skills/harms-check - ice-score
plugins/mycelium/skills/ice-score - interview
plugins/mycelium/skills/interview - jtbd-map
plugins/mycelium/skills/jtbd-map - launch-tier
plugins/mycelium/skills/launch-tier - log-evidence
plugins/mycelium/skills/log-evidence - metrics-detect
plugins/mycelium/skills/metrics-detect - metrics-pull
plugins/mycelium/skills/metrics-pull - migrate-from-legacy
plugins/mycelium/skills/migrate-from-legacy - mocked-persona-interview
plugins/mycelium/skills/mocked-persona-interview - ost-builder
plugins/mycelium/skills/ost-builder - ost-render
plugins/mycelium/skills/ost-render - ping
plugins/mycelium/skills/ping - preflight
plugins/mycelium/skills/preflight - privacy-check
plugins/mycelium/skills/privacy-check - prompt-optimizer
plugins/mycelium/skills/prompt-optimizer - purpose-properties
plugins/mycelium/skills/purpose-properties - receipt-render
plugins/mycelium/skills/receipt-render - reflexion
plugins/mycelium/skills/reflexion - regulatory-review
plugins/mycelium/skills/regulatory-review - render
plugins/mycelium/skills/render - retrospective
plugins/mycelium/skills/retrospective - scaffold-cost-check
plugins/mycelium/skills/scaffold-cost-check - security-review
plugins/mycelium/skills/security-review - service-check
plugins/mycelium/skills/service-check - setup
plugins/mycelium/skills/setup - start
plugins/mycelium/skills/start - team-shape
plugins/mycelium/skills/team-shape - theory-fidelity
plugins/mycelium/skills/theory-fidelity - threat-model
plugins/mycelium/skills/threat-model - usability-check
plugins/mycelium/skills/usability-check - user-interview
plugins/mycelium/skills/user-interview - user-needs-map
plugins/mycelium/skills/user-needs-map - wardley-map
plugins/mycelium/skills/wardley-map - wiring-contract
plugins/mycelium/skills/wiring-contract - xai-check
plugins/mycelium/skills/xai-check - interview
tests/bash/fixtures/check_15/compliant/plugins/mycelium/skills/interview - new_user_intake
tests/bash/fixtures/check_15/heuristic_candidate/plugins/mycelium/skills/new_user_intake - interview
tests/bash/fixtures/check_15/missing_wrapping/plugins/mycelium/skills/interview - badskill
tests/bash/fixtures/check_31/missing_preflight/plugins/mycelium/skills/badskill - goodskill
tests/bash/fixtures/check_31/present/plugins/mycelium/skills/goodskill - diamond-assess
tests/bash/fixtures/check_41/missing_preamble/plugins/mycelium/skills/diamond-assess - diamond-assess
tests/bash/fixtures/check_41/with_preamble/plugins/mycelium/skills/diamond-assess - dora-check
tests/bash/fixtures/check_42/missing_preamble/plugins/mycelium/skills/dora-check - dora-check
tests/bash/fixtures/check_42/with_preamble/plugins/mycelium/skills/dora-check - ost-render
tests/bash/fixtures/check_43/invalid_value/plugins/mycelium/skills/ost-render - ost-render
tests/bash/fixtures/check_43/missing_body/plugins/mycelium/skills/ost-render - ost-render
tests/bash/fixtures/check_43/missing_frontmatter/plugins/mycelium/skills/ost-render - ost-render
tests/bash/fixtures/check_43/valid_none/plugins/mycelium/skills/ost-render - ost-render
tests/bash/fixtures/check_43/valid_yes/plugins/mycelium/skills/ost-render - bvssh-check
tests/bash/fixtures/check_45/compliant/plugins/mycelium/skills/bvssh-check - ice-score
tests/bash/fixtures/check_45/compliant/plugins/mycelium/skills/ice-score - bvssh-check
tests/bash/fixtures/check_45/missing_marker/plugins/mycelium/skills/bvssh-check - ice-score
tests/bash/fixtures/check_45/missing_marker/plugins/mycelium/skills/ice-score - canvas-update
tests/bash/fixtures/check_5/all_present/plugins/mycelium/skills/canvas-update - canvas-update
tests/bash/fixtures/check_5/missing_canvas_in_mapping/plugins/mycelium/skills/canvas-update - bad_skill
tests/bash/fixtures/check_8/missing_name/plugins/mycelium/skills/bad_skill - good_skill
tests/bash/fixtures/check_8/valid/plugins/mycelium/skills/good_skill
How it works
a11y-check
When your agent uses it
Accessibility audit, scoped to the surfaces a product actually has. Detects web / rendered_markdown / terminal / native_app / video_audio / document / headless, then applies only the criteria that bind. WCAG 2.1 AA in full for web; not at all for headless.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
1,790 tokensWhen the skill is activated
Reference documents
18,786 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- STEP 1 — SURFACE GATE. Run this BEFORE the checklist, every time.
- STEP 2 — WCAG 2.1 AA Checklist by Principle
- Automated Testing Tools (by stack)
- Common Violations and Fixes
- When to Run
- Sensitive Context Note
- Neurodiversity Considerations
Scripts executed separately
../../hooks/absence-claim-guard.sh../../hooks/autonomous-evidence-guard.sh../../hooks/bash-state-guard.sh../../hooks/brownfield-gate.sh../../hooks/canvas-schema-check.sh../../hooks/change-log.sh../../hooks/ci-signal.sh../../hooks/codex-postfailure-shim.sh../../hooks/contract-part.sh../../hooks/correction-attribution-guard.sh../../hooks/diamond-state-audit.sh../../hooks/discovery-gate.sh../../hooks/discovery-trigger-guard.sh../../hooks/exposure-change.sh../../hooks/exposure-gate.sh../../hooks/framework-guard.sh../../hooks/gate-override-check.sh../../hooks/gate.sh../../hooks/guard-state-gate.sh../../hooks/install-runtime-hooks.sh../../hooks/key-shape-guard.sh../../hooks/lesson-triggers.sh../../hooks/next-action-check.sh../../hooks/next-item-repeat.sh../../hooks/post-write-nudge.sh../../hooks/preflight.sh../../hooks/read-before-research-guard.sh../../hooks/read-log.sh../../hooks/reflexion-gate.sh../../hooks/scale-lock-gate.sh../../hooks/scope-gate.sh../../hooks/session-start.sh../../hooks/shell-safety-guard.sh../../hooks/stop-check.sh../../scripts/codex_plugin_hooks.py
Files
../../../../.claude-plugin/marketplace.jsonasset1,133 bytes../../.claude-plugin/icon.pngasset107,898 bytes../../.claude-plugin/plugin.jsonasset1,134 bytes../../domains/quality/CLAUDE.mddoc10,373 bytes../../hooks/README.mddoc66,550 bytes../../hooks/absence-claim-guard.shruns2,712 bytes../../hooks/autonomous-evidence-guard.shruns3,052 bytes../../hooks/bash-state-guard.shruns1,779 bytes../../hooks/brownfield-gate.shruns5,762 bytes../../hooks/canvas-schema-check.shruns1,408 bytes../../hooks/change-log.shruns2,319 bytes../../hooks/ci-signal.shruns2,862 bytes../../hooks/codex-postfailure-shim.shruns2,213 bytes../../hooks/contract-part.shruns923 bytes../../hooks/correction-attribution-guard.shruns2,578 bytes../../hooks/diamond-state-audit.shruns3,173 bytes../../hooks/discovery-gate.shruns13,487 bytes../../hooks/discovery-trigger-guard.shruns2,482 bytes../../hooks/exposure-change.shruns1,252 bytes../../hooks/exposure-gate.shruns5,918 bytes../../hooks/framework-guard.shruns5,427 bytes../../hooks/gate-override-check.shruns5,694 bytes../../hooks/gate.shruns13,004 bytes../../hooks/guard-state-gate.shruns3,329 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex-plugin.jsonasset14,331 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.codex.jsonasset14,767 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.cursor.jsonasset9,136 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/hooks.jsonasset20,541 bytes../../hooks/install-runtime-hooks.shruns5,832 bytes../../hooks/key-shape-guard.shruns1,307 bytes../../hooks/lesson-triggers.shruns2,943 bytes../../hooks/next-action-check.shruns8,404 bytes../../hooks/next-item-repeat.shruns2,716 bytes../../hooks/post-write-nudge.shruns10,744 bytes../../hooks/preflight.shruns15,101 bytes../../hooks/pretooluse-on-failure.txtdoc5,246 bytes../../hooks/read-before-research-guard.shruns1,914 bytes../../hooks/read-log.shruns5,530 bytes../../hooks/reflexion-gate.shruns7,980 bytes../../hooks/scale-lock-gate.shruns4,159 bytes../../hooks/scope-gate.shruns6,545 bytes../../hooks/session-start.shruns91,150 bytes../../hooks/shell-safety-guard.shruns3,622 bytes../../hooks/stop-check.shruns16,920 bytes../../scripts/codex_plugin_hooks.pyruns3,131 bytesSKILL.mdcore7,245 bytes../../../../tests/bash/fixtures/check_12/aligned/.claude-plugin/marketplace.jsonasset59 bytes../../../../tests/bash/fixtures/check_12/aligned/plugins/mycelium/.claude-plugin/plugin.jsonasset91 bytes../../../../tests/bash/fixtures/check_12/mismatch/plugins/mycelium/.claude-plugin/plugin.jsonasset91 bytes../../../../tests/bash/fixtures/check_30/version_drift/plugins/mycelium/.claude-plugin/plugin.jsonasset149 bytes../../../../tests/bash/fixtures/check_30/version_synced/plugins/mycelium/.claude-plugin/plugin.jsonasset150 bytes../../../../tests/bash/fixtures/check_44/aligned/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/aligned/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/aligned/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/aligned/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/codex_drift/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/codex_drift/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/codex_drift/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/codex_drift/plugins/mycelium/hooks/hooks.jsonasset384 bytes../../../../tests/bash/fixtures/check_44/missing_script/plugins/mycelium/hooks/hooks.jsonasset468 bytes../../../../tests/bash/fixtures/check_44/missing_script/plugins/mycelium/hooks/hooks.jsonasset468 bytes../../../../tests/bash/fixtures/check_44/missing_script/plugins/mycelium/hooks/hooks.jsonasset468 bytes../../../../tests/bash/fixtures/check_44/missing_script/plugins/mycelium/hooks/hooks.jsonasset468 bytes../../../../tests/bash/fixtures/check_44/missing_script/plugins/mycelium/hooks/hooks.jsonasset468 bytes../../../../tests/bash/fixtures/check_46/bad/.claude-plugin/marketplace.jsonasset102 bytes../../../../tests/bash/fixtures/check_46/good/.claude-plugin/marketplace.jsonasset102 bytes../../../../tests/bash/fixtures/check_47/bad/plugins/mycelium/hooks/hooks.jsonasset156 bytes../../../../tests/bash/fixtures/check_47/bad/plugins/mycelium/hooks/hooks.jsonasset156 bytes../../../../tests/bash/fixtures/check_47/good/plugins/mycelium/hooks/hooks.jsonasset156 bytes../../../../tests/bash/fixtures/check_47/good/plugins/mycelium/hooks/hooks.jsonasset156 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.jsonasset6,787 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes../../../../tests/bash/fixtures/check_55/good/plugins/mycelium/hooks/hooks.jsonasset7,006 bytes
Read SKILL.md
# Accessibility Audit
Evaluate user-facing work against the criteria that BIND TO ITS SURFACES. Accessibility is a design
constraint, not a polish step (Downe Principle 11) — and an instrument aimed at a surface the product
does not have measures nothing while looking like a failure.
## STEP 1 — SURFACE GATE. Run this BEFORE the checklist, every time.
**The checklist below is written for web pages. Most products are not web pages.** Detect which
user-facing surfaces this product actually has, from the repository, and evaluate ONLY the criteria
that bind to them. Profiles and detection hints: `engine/canvas-guidance.yml#surfaces` —
`web` · `rendered_markdown` · `terminal` · `native_app` · `video_audio` · `document` · `headless`.
A product commonly has several. State which you found and how, in the output.
adopt
When your agent uses it
Bring Mycelium into a project that already has code. Detects that the repo predates the framework, asks before touching anything, then reads the codebase to draft what it CAN establish (delivery, solution shape) and — the actual point — names what it cannot (purpose, strategy, real user evidence). The output is a discovery backlog with a head start, never a filled canvas.
What it loads into context
Frontmatter
168 tokensAlways available to the agent
SKILL.md
3,153 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First: are Mycelium's hooks running here? (v0.286.0)
- When to Use
- The shape of the run: two phases, one session
- Workflow
- What NOT to Do
- Theory Citations
Scripts executed separately
../../scripts/advisory_ledger.py../../scripts/advisory_ledger.py../../scripts/advisory_ledger.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../scripts/advisory_ledger.pyruns27,019 bytes../../scripts/advisory_ledger.pyruns27,019 bytes../../scripts/advisory_ledger.pyruns27,019 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore13,026 bytesSKILL.mdcore13,026 bytesSKILL.mdcore13,026 bytes
Read SKILL.md
# Adopt (brownfield entry)
## First: are Mycelium's hooks running here? (v0.286.0)
Run `find .claude/state/hooks-alive "${TMPDIR:-/tmp}/mycelium-hooks-alive-$(id -u)" -mmin -60 2>/dev/null`. If it prints a path (since v0.318.0 the hooks also stamp the temp folder in a project with no Mycelium state yet, where they do nothing else), say nothing
about it and go on. If it prints nothing, Mycelium's hooks did not run in this session: its gates
and the rules it gives the agent at session start are off, and nothing else will say so. Tell the
user in one line before anything else: "Mycelium's hooks are not running in this session, so its
gates are off. On Codex CLI, open `/hooks`, trust Mycelium's hooks and start a new session; on
Claude Code, check the plugin is enabled in `/plugin`." Then carry on with this skill.
`/mycelium:start` assumes a blank page. Most projects are not a blank page. This
skill is the entry point when the code came first.
assumption-test
When your agent uses it
Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework, organized by Gilad's AFTER model (Assessment → Fact-Finding → Tests → Experiments → Release Results).
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
6,187 tokensWhen the skill is activated
Reference documents
6,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Assumption Types (Torres / Cagan)
- Step 1: Map Assumptions
- Step 2: Prioritize (2x2 Matrix)
- Step 3: Choose the Lightest Test
- Step 4: Define Success Criteria
- Step 5: State Your Prediction (before running)
- Step 5b: Write it down where something can find it (the output contract)
- Step 6: Run and Interpret
- Bias Warning
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytesSKILL.mdcore25,573 bytes
Read SKILL.md
# Assumption Testing
Every solution rests on assumptions. Test the riskiest ones first with the lightest method possible.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
bias-check
When your agent uses it
Use before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
2,024 tokensWhen the skill is activated
Reference documents
23,172 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Workflow
- When to Surface This Skill
- Canvas Output
- Recording the Bias gate
- Decision Log (MANDATORY per G-P4)
- Theory Citations
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/theory-gates.mddoc56,781 bytes../../harness/cognitive-biases.mddoc17,853 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytes
Read SKILL.md
# Bias Check Skill
Pre-research and pre-decision bias review.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
bvssh-check
When your agent uses it
Use to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
2,939 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Output
- Canvas (MANDATORY — the source of truth, do this FIRST)
- Decision Log (MANDATORY per G-P4)
- Prior findings first (added v0.96.0)
- Theory Citations
Scripts executed separately
../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_wiring.py../../scripts/check_wiring_contract.py../../scripts/check_wiring_contract.py../../scripts/check_wiring_contract.py
Files
../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_wiring.pyruns24,819 bytes../../scripts/check_wiring_contract.pyruns17,804 bytes../../scripts/check_wiring_contract.pyruns17,804 bytes../../scripts/check_wiring_contract.pyruns17,804 bytesSKILL.mdcore12,305 bytesSKILL.mdcore12,305 bytesSKILL.mdcore12,305 bytes
Read SKILL.md
# BVSSH Check Skill
Evaluate alignment with Better Value Sooner Safer Happier.
## Workflow
For each dimension, assess current state:
### Better
- [ ] Quality improving or stable (not degrading)?
- [ ] Technical debt under control (not growing unchecked)?
- [ ] User satisfaction metrics stable or improving?
- [ ] Defect rate stable or declining?
- Evidence: [cite specific metrics or observations]canvas-health
When your agent uses it
Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
18,414 tokensWhen the skill is activated
Reference documents
1,802 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Output Format
- Canvas-recorded framework version vs installed (added v0.90.0)
- Decision-log reconcile — a dated event whose canvas row was never written
- A canvas file that claims to be assessed and holds nothing
- The checks the session-start NEXT ITEM sends here (added v0.328.5)
- Upstream candidate registry — is surfaced friction already fixed?
- Findings that name people, and no task that reaches them
- Contacts recorded as prose, never as a touch
- touch_log order — is the last entry actually the most recent?
- Instrument contract — frozen predictions with no home, no expiry, or silent edits
- Climatic predictions due for scoring (added v0.95.0)
- Evidence breadth (G-D2 / G-D4)
- Theory Citations
- Postflight: Verify-After-Write (claim matches state)
- Content in key position (added 2026-08-31, founder ruling)
- A pointer that names nothing (added v0.215.0)
- Has a Definition of Done turned into a log? (added v0.225.0)
- Is each OST node a user need, or a maintenance ticket? (added v0.215.0, founder 2026-09-02)
- The calibration loop: fed, due, or blamed on the wrong reason (added v0.216.0)
- A claim of novelty says what it was checked against (added v0.208.0, founder ruling 2026-09-14)
- Derived fields: a value that names its source is read from it (added v0.218.0)
- Fields the canvas writes that no schema declares (added 2026-08-31)
Scripts executed separately
../../scripts/advisory_ledger.py../../scripts/advisory_ledger.py../../scripts/advisory_ledger.py../../scripts/check_assessment_landed.py../../scripts/check_canvas_version_drift.py../../scripts/check_citations.py../../scripts/check_climatic_predictions.py../../scripts/check_contact_recorded_as_prose.py../../scripts/check_cynefin_freshness.py../../scripts/check_derived_fields.py../../scripts/check_dod_shape.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_landing.py../../scripts/check_evidence_links.py../../scripts/check_field_wiring.py../../scripts/check_hook_delivery.py../../scripts/check_hook_delivery.py../../scripts/check_hook_delivery.py../../scripts/check_hook_delivery.py../../scripts/check_ice_aggregate.py../../scripts/check_idle_opportunities.py../../scripts/check_idle_opportunities.py../../scripts/check_idle_opportunities.py../../scripts/check_idle_opportunities.py../../scripts/check_idle_opportunities.py../../scripts/check_idle_opportunities.py../../scripts/check_instrument_contract.py../../scripts/check_key_shape.py../../scripts/check_log_reconcile.py../../scripts/check_merge_markers.py../../scripts/check_named_people_unactioned.py../../scripts/check_opportunity_shape.py../../scripts/check_published_records.py../../scripts/check_published_records.py../../scripts/check_published_records.py../../scripts/check_published_records.py../../scripts/check_published_records.py../../scripts/check_published_records.py../../scripts/check_reply_owed.py../../scripts/check_source_authenticity.py../../scripts/check_source_authenticity.py../../scripts/check_source_authenticity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_class_fidelity.py../../scripts/check_source_independence.py../../scripts/check_stale_prose.py../../scripts/check_touch_log_order.py../../scripts/check_upstream_candidates.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/canvas-guidance.ymlasset56,574 bytes../../engine/evidence-decay.mddoc7,883 bytes../../scripts/advisory_ledger.pyruns27,019 bytes../../scripts/advisory_ledger.pyruns27,019 bytes../../scripts/advisory_ledger.pyruns27,019 bytes../../scripts/check_assessment_landed.pyruns9,594 bytes../../scripts/check_canvas_version_drift.pyruns5,661 bytes../../scripts/check_citations.pyruns7,846 bytes../../scripts/check_climatic_predictions.pyruns10,060 bytes../../scripts/check_contact_recorded_as_prose.pyruns8,358 bytes../../scripts/check_cynefin_freshness.pyruns13,529 bytes../../scripts/check_derived_fields.pyruns7,828 bytes../../scripts/check_dod_shape.pyruns9,849 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_landing.pyruns12,109 bytes../../scripts/check_evidence_links.pyruns30,902 bytes../../scripts/check_field_wiring.pyruns18,661 bytes../../scripts/check_hook_delivery.pyruns9,794 bytes../../scripts/check_hook_delivery.pyruns9,794 bytes../../scripts/check_hook_delivery.pyruns9,794 bytes../../scripts/check_hook_delivery.pyruns9,794 bytes../../scripts/check_ice_aggregate.pyruns18,621 bytes../../scripts/check_idle_opportunities.pyruns9,188 bytes../../scripts/check_idle_opportunities.pyruns9,188 bytes../../scripts/check_idle_opportunities.pyruns9,188 bytes../../scripts/check_idle_opportunities.pyruns9,188 bytes../../scripts/check_idle_opportunities.pyruns9,188 bytes../../scripts/check_idle_opportunities.pyruns9,188 bytes../../scripts/check_instrument_contract.pyruns43,273 bytes../../scripts/check_key_shape.pyruns13,738 bytes../../scripts/check_log_reconcile.pyruns16,890 bytes../../scripts/check_merge_markers.pyruns6,259 bytes../../scripts/check_named_people_unactioned.pyruns4,395 bytes../../scripts/check_opportunity_shape.pyruns7,467 bytes../../scripts/check_published_records.pyruns8,441 bytes../../scripts/check_published_records.pyruns8,441 bytes../../scripts/check_published_records.pyruns8,441 bytes../../scripts/check_published_records.pyruns8,441 bytes../../scripts/check_published_records.pyruns8,441 bytes../../scripts/check_published_records.pyruns8,441 bytes../../scripts/check_reply_owed.pyruns10,339 bytes../../scripts/check_source_authenticity.pyruns22,535 bytes../../scripts/check_source_authenticity.pyruns22,535 bytes../../scripts/check_source_authenticity.pyruns22,535 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_class_fidelity.pyruns16,688 bytes../../scripts/check_source_independence.pyruns21,645 bytes../../scripts/check_stale_prose.pyruns14,877 bytes../../scripts/check_touch_log_order.pyruns5,295 bytes../../scripts/check_upstream_candidates.pyruns9,520 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytesSKILL.mdcore74,927 bytes
Read SKILL.md
# Canvas Health Check
Audit the canvas knowledge base for quality, consistency, and completeness. The canvas is Mycelium's source of truth -- its quality directly determines agent output quality (Raschka: "context quality = model quality").
## When to Use
- Before any diamond records a decision (called automatically by `/mycelium:diamond-assess`)
- After a period of inactivity (>7 days since last canvas update)
- When agent output quality seems to degrade
- After onboarding a new team member (ensures canvas is self-explanatory)
- Proactively: run periodically to catch silent drift
## Workflow
canvas-sync
When your agent uses it
Synchronize canvas state across team sessions via git. Ensures all team members see the same product knowledge.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
412 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
Files
SKILL.mdcore1,829 bytesSKILL.mdcore1,829 bytes
Read SKILL.md
# Canvas Sync
## When to Use
- Starting a new session (pull latest canvas)
- Ending a session (commit canvas changes)
- After team discussion that changes product direction
- When canvas conflicts arise from parallel work
## Workflow
### Pull Latest
```
git pull origin main
```canvas-update
When your agent uses it
Update canvas sections with new evidence. Ensures canvas stays current as the single source of truth.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,927 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Rules
- Which Canvas File for Which Information
- Workflow
- Output to the user
- Counter-Argument Check (Bias Mitigation)
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore7,900 bytesSKILL.mdcore7,900 bytesSKILL.mdcore7,900 bytes
Read SKILL.md
# Canvas Update
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
```
grep -o "<prefix>-[0-9][0-9]*" .claude/canvas/<file>.yml | sort -u -t- -k2 -n | tail -3corrections-audit
When your agent uses it
Use to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
3,699 tokensWhen the skill is activated
Reference documents
20,402 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Attribution: run the script, do not count by hand
- When to Use
- Workflow
- Output Format
- Prior findings first (added v0.96.0)
- Theory Citations
Scripts executed separately
../../scripts/check_correction_attribution.py
Files
../../engine/consistency-check-spec.mddoc34,033 bytes../../engine/warning-handbook.mddoc8,013 bytes../../harness/anti-patterns.mddoc47,849 bytes../../scripts/check_correction_attribution.pyruns11,859 bytesSKILL.mdcore16,354 bytesSKILL.mdcore16,354 bytesSKILL.mdcore16,354 bytesSKILL.mdcore16,354 bytes
Read SKILL.md
# Corrections Audit Skill
Analyze corrections.md for trends, recurring patterns, and actionable insights.
## Attribution: run the script, do not count by hand
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_correction_attribution.py" --root . --snapshot
```
**Added 2026-08-03.** This audit's headline number — *who caught the mistake* —
was computed by hand and had been produced exactly twice, six weeks apart, each
time because a human remembered to look. It is the only number that answers thecount
When your agent uses it
Print your own north-star row from your own record, and nothing else. Reads .claude/harness/decision-log.md, the canvas and the hook logs in this project; prints one line (decisions before the first source file, of which citing outside evidence, kills before code, sessions). Sends nothing anywhere. Opt-in; paste the line where you like or not at all.
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
734 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Run
- What the numbers are, and which are proxies
- Rules
Scripts executed separately
../../scripts/count_builder_row.py
Files
../../scripts/count_builder_row.pyruns7,641 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytesSKILL.mdcore3,056 bytes
Read SKILL.md
# Count: your own row, from your own record
Mycelium's north star is a hypothesis (dogfood DL-1177, 2026-09-07): a builder who makes at least
one build-or-kill decision on evidence from outside their own head, before their project's first
source file, is the builder who comes back and later says the brief changed what they built. There
is no telemetry by design (PRIVACY.md). This command is the opt-in half: it reads your repository
and prints one line. It writes nothing and sends nothing.
## Run
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/count_builder_row.py" --project-dir .
```
cycle-render
When your agent uses it
Render `.claude/canvas/cycle-history.yml` as a Gantt chart + outcome distribution pie (or ascii / json). Read-only. Consults the attribution registry per `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` consent + privacy gate. Third specialist in the render fleet.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
4,412 tokensWhen the skill is activated
Reference documents
5,397 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When NOT to use
- Identifier exposure
- Preflight: Read sources
- Arguments
- Workflow
- Rules
- Counter-Argument Check
- What this skill does NOT do
- Test fixtures (G-V12 / Check 37)
- Theory citations
Scripts executed separately
../../scripts/validate_mermaid.py
Files
../../engine/render-conventions.mddoc22,944 bytes../../scripts/validate_mermaid.pyruns7,553 bytesSKILL.mdcore17,025 bytesSKILL.mdcore17,025 bytes
Read SKILL.md
# Cycle Render
Read-only render of `.claude/canvas/cycle-history.yml` as gantt + pie + (optionally) json. Third specialist in the render fleet. See `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` for shared conventions.
## When NOT to use
- For cross-cutting opportunity→solution→cycle traceability view → dispatcher's `/mycelium:render --view traceability` (deferred to Phase 4a–4d research-first methodology).
- To RECORD a new cycle outcome → `/mycelium:retrospective`, `/mycelium:ice-score` (on discard), or `/mycelium:launch-tier` (on launch). This skill is read-only.
- For framework-health full assessment → `/mycelium:framework-health`. cycle-render emits one visualization piece; framework-health is the broader audit.
## Identifier exposure
**Declared**: YES
cynefin-classify
When your agent uses it
Use when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate methods.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
2,319 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Workflow
- Canvas Output
- Liminal Zones (Snowden, 2019 — Confused followed in 2020)
- Decision Log (MANDATORY per G-P4)
- Theory Citations
- Postflight: Verify-After-Write (claim matches state)
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore9,429 bytes
Read SKILL.md
# Cynefin Classify Skill
Classify problem domain and route to appropriate methods.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
define-done
When your agent uses it
Pin a measurable, outcome-based Definition of Done for a diamond — a behaviour-change that creates value, not a build-list. Problem-first Socratic sequence; writes definition_of_done to the diamond at birth or retrofits it when missing.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
5,216 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Preflight: Read target file before any Write/Edit
- The sequence (Socratic, problem-first)
- Per-scale "done" + lead/lag defaults
- Build-mode gate — refuse build-to-earn during build-to-learn
- Write the field
- Purpose-stance check on the bar you just wrote (WARN — never blocks)
- Failure-mode guards (baked in)
- Provisional wording
- Theory Citations
Scripts executed separately
../../scripts/check_dod_shape.py../../scripts/check_purpose_stance.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../scripts/check_dod_shape.pyruns9,849 bytes../../scripts/check_purpose_stance.pyruns35,897 bytesSKILL.mdcore21,566 bytesSKILL.mdcore21,566 bytes
Read SKILL.md
# Define Done
Pin an explicit, outcome-based **Definition of Done** for a diamond. "Done" is *a change in human behaviour that creates value* (Seiden), not "the feature shipped" — you're done when it ships **and** has the intended impact (Amplitude). The diamond's implicit done defaults to the harshest, least-controllable bar ("a user shipped a product"), which is both wrong for validating *purpose* and a demotivation engine. This skill makes the bar explicit, measurable, and pre-committed.
This is distinct from `/mycelium:definition-of-done` (the per-feature agile *quality checklist* run at `close`). This skill sets the **outcome bar a whole diamond is judged against**; that one verifies a feature meets quality criteria. Both can apply.
## When to use
- **At diamond birth** — `/mycelium:interview` (L0) and child-diamond spawn (`/mycelium:diamond-progress`) call this before a diamond is "live."
- **Retrofit** — when `/mycelium:canvas-health`, `/mycelium:diamond-assess`, or the SessionStart nudge flags a diamond with no `definition_of_done`.
- Never silent-fill. The *question* is what produces a real bar ("fits, not ships"); a back-filled field is theatre.
## Preflight: Read target file before any Write/Edit
definition-of-done
When your agent uses it
Use to verify a feature/story meets all Definition of Done criteria before marking complete.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
2,276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Completion Audit: Anti-Bias Clauses
- Checklist
- Mechanised proxy check — run these before ticking anything
- Outcome
- Theory Citations
Scripts executed separately
../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_negative_control.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_test_authenticity.py../../scripts/check_wiring.py
Files
../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_negative_control.pyruns11,303 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_test_authenticity.pyruns19,331 bytes../../scripts/check_wiring.pyruns24,819 bytesSKILL.mdcore9,746 bytesSKILL.mdcore9,746 bytes
Read SKILL.md
# Definition of Done Skill
DoD checklist enforcement.
## Completion Audit: Anti-Bias Clauses
Before checking any item below as DONE, perform a completion audit against the actual current state, not against intent or memory:
- **Restate the acceptance criteria** as concrete deliverables. Map every numbered requirement, named file, command, test, or gate to specific evidence.
- **Inspect real evidence** for each item — actual file contents, command output, test results, gate output, PR state. Not "I implemented it" — "here is the file at this path showing it."
- **Verify proxies actually cover the requirement.** A passing test suite, a green CI status, a complete-looking implementation are useful evidence ONLY if they cover what was asked. A test that passes but doesn't exercise the new code is not coverage. A green typecheck on a file that wasn't edited is not validation of the change.
- **Treat uncertainty as not-done.** If you can't verify an item with evidence, the item is NOT DONE. Do more verification or continue the work.
Do not rely on any of the following as proof of completion:delivery-bootstrap
When your agent uses it
Use when starting implementation on a new or unfamiliar codebase. Auto-detects tech stack and sets up development context.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
2,261 tokensWhen the skill is activated
Reference documents
6,998 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Rules
- Canvas Output
- Theory Citations
Files
../../jit-tooling/active-stack.example.ymlasset921 bytes../../jit-tooling/detector.mddoc26,354 bytes../../jit-tooling/security-scanning.mddoc1,888 bytesSKILL.mdcore9,096 bytes
Read SKILL.md
# Delivery Bootstrap Skill
Just-in-Time tech stack detection and setup.
## Workflow
1. **Check product_type** from `.claude/diamonds/active.yml`:
- If `product_type` is set (from `/mycelium:interview`), use it to determine the delivery profile.
- If not set, scan for indicators per `${CLAUDE_PLUGIN_ROOT}/jit-tooling/detector.md` Step 1b:
- Curriculum/lesson plans, LMS config -> `content_course`
- Manuscript/chapters, editorial calendar -> `content_publication`
- Video scripts, subtitle files, podcast RSS -> `content_media`
- Prompt templates, model configs, agent definitions -> `ai_tool`
- Service blueprints, pricing docs -> `service_offering`devils-advocate
When your agent uses it
Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
3,058 tokensWhen the skill is activated
Reference documents
3,112 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Technique 1: Pre-Mortem
- Technique 2: Assumption Reversal
- Technique 3: Red Team
- 10 Challenge Questions
- Technique 4: Attribution-vs-Consistency Check
- Technique 5: Ambient triggering on assertion-shaped patterns
- Technique 7: Blind adversarial pass — measured well when run, and rarely run
- Technique 6: Cunningham's Law check (publish-rough-then-iterate)
- When to Use
- Output
Files
../../engine/reading-for-meaning.mddoc4,338 bytes../../engine/status-translations.mddoc9,460 bytesSKILL.mdcore13,754 bytes
Read SKILL.md
# Devil's Advocate
Run before every major diamond transition and architecture decision. Source: Kahneman, Shotton.
## Technique 1: Pre-Mortem
Imagine it's 6 months from now and this decision FAILED spectacularly.
1. What went wrong?
2. What assumption was the weakest link?
3. What signal did we ignore?
4. Who was affected and how?
## Technique 2: Assumption Reversal
For each key assumption:
- State the assumption explicitlydiamond-assess
When your agent uses it
Use to evaluate the current state of a diamond. Checks theory gates, confidence levels, and recommends next action.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
7,401 tokensWhen the skill is activated
Reference documents
32,837 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First: are Mycelium's hooks running here? (v0.286.0)
- Preflight: Read-before-Recommend (gate-narration discipline)
- Workflow
- Closing path (derive it; do not make the human ask for it)
- Purpose-properties state (report it, do not fix it here)
- Output Format
- Theory Citations
Scripts executed separately
../../scripts/check_dod_shape.py../../scripts/check_purpose_stance.py../../scripts/check_scale_occupancy.py../../scripts/derive_closing_path.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/autonomous-mode.mddoc16,821 bytes../../engine/confidence-thresholds.ymlasset24,591 bytes../../engine/perspective-resolution.mddoc5,982 bytes../../engine/status-translations.mddoc9,460 bytes../../engine/theory-gates.mddoc56,781 bytes../../engine/wayfinding.mddoc7,445 bytes../../harness/anti-patterns.mddoc47,849 bytes../../scripts/check_dod_shape.pyruns9,849 bytes../../scripts/check_purpose_stance.pyruns35,897 bytes../../scripts/check_scale_occupancy.pyruns8,670 bytes../../scripts/derive_closing_path.pyruns52,232 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore30,595 bytesSKILL.mdcore30,595 bytesSKILL.mdcore30,595 bytesSKILL.mdcore30,595 bytesSKILL.mdcore30,595 bytes
Read SKILL.md
# Diamond Assess Skill
## First: are Mycelium's hooks running here? (v0.286.0)
Run `find .claude/state/hooks-alive "${TMPDIR:-/tmp}/mycelium-hooks-alive-$(id -u)" -mmin -60 2>/dev/null`. If it prints a path (since v0.318.0 the hooks also stamp the temp folder in a project with no Mycelium state yet, where they do nothing else), say nothing
about it and go on. If it prints nothing, Mycelium's hooks did not run in this session: its gates
and the rules it gives the agent at session start are off, and nothing else will say so. Tell the
user in one line before anything else: "Mycelium's hooks are not running in this session, so its
gates are off. On Codex CLI, open `/hooks`, trust Mycelium's hooks and start a new session; on
Claude Code, check the plugin is enabled in `/plugin`." Then carry on with this skill.
Evaluate current diamond state and recommend next action.
## Preflight: Read-before-Recommend (gate-narration discipline)diamond-progress
When your agent uses it
Record a diamond's next decision (set_target; start_experiment and commit_to_build; release; close; an L0's state_purpose or review). Runs the theory gates each decision needs, validates evidence, and at close runs the executable Definition of Done checklist.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
15,590 tokensWhen the skill is activated
Reference documents
28,093 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Preflight: Read-before-Recommend (gate-narration discipline)
- Workflow
- Executable Definition of Done (at `close` ONLY)
- Non-Progression Paths: Pivot, Park, Kill
- Purpose-stance gate (at `commit_to_build` and `release`)
- Learning Capture (After Every Decision)
- Post-Build Next-Steps Nudge (at `release`, and after any build or POC produces working code)
- Theory Citations
- Counter-Argument Check (Bias Mitigation)
Scripts executed separately
../../scripts/check_purpose_stance.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/autonomous-mode.mddoc16,821 bytes../../engine/canvas-guidance.ymlasset56,574 bytes../../engine/confidence-thresholds.ymlasset24,591 bytes../../engine/perspective-resolution.mddoc5,982 bytes../../engine/status-translations.mddoc9,460 bytes../../engine/theory-gates.mddoc56,781 bytes../../engine/wayfinding.mddoc7,445 bytes../../scripts/check_purpose_stance.pyruns35,897 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore64,105 bytesSKILL.mdcore64,105 bytesSKILL.mdcore64,105 bytesSKILL.mdcore64,105 bytesSKILL.mdcore64,105 bytesSKILL.mdcore64,105 bytes
Read SKILL.md
# Diamond Progress Skill
Record a diamond's decisions, each through the theory gates it needs. Where a diamond is, is read from its decisions ("target set", "committed to build", "released", "closed"; discovery until `commit_to_build`, delivery after; DL-1368, DL-1372). At `close`, runs an executable checklist that GATES it.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
## Preflight: Read-before-Recommend (gate-narration discipline)
**Hard rule** (per the operating contract's Communication Rules, anti-pattern #7 graduation v0.39.16). Every gate-status narration, blocker statement, hold claim, theory-gate verdict, or transition-blocked finding this skill emits MUST cite the canvas file + field path of the source evidence. Adjacent-surface inference (different opportunity, different ht, different topic) MUST be tagged as inference, not asserted as gate state. Companion to the Read-before-Write rule above: that one protects what gets WRITTEN to canvas; this one protects what gets CLAIMED about canvas state in the skill's narration.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).diamond-render
When your agent uses it
Render `.claude/diamonds/active.yml` as the decisions each diamond has recorded, in order, grouped by mode (discovery, delivery). Read-only. Default format Mermaid stateDiagram-v2, drawn by a script. Recommended at the end of `/mycelium:diamond-assess` so every assessment closes with a visual state-of-play. See `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` for shared render fleet conventions.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
2,264 tokensWhen the skill is activated
Reference documents
5,397 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When NOT to use
- Identifier exposure
- Arguments
- Workflow
- Rules
- Counter-Argument Check
- What this skill does NOT do
- Recommend-not-invoke from `/mycelium:diamond-assess`
- Tests
- Theory citations
Scripts executed separately
../../scripts/render_diamonds.py../../scripts/validate_mermaid.py
Files
../../engine/render-conventions.mddoc22,944 bytes../../scripts/render_diamonds.pyruns10,841 bytes../../scripts/validate_mermaid.pyruns7,553 bytesSKILL.mdcore8,778 bytesSKILL.mdcore8,778 bytesSKILL.mdcore8,778 bytesSKILL.mdcore8,778 bytes
Read SKILL.md
# Diamond Render
Read-only render of `.claude/diamonds/active.yml`. First specialist of the render fleet (with
`/mycelium:ost-render`, `/mycelium:cycle-render` and the dispatcher `/mycelium:render`).
**What it draws (v0.309.0, stage 5d-3, founder ruling DL-1372 V4).** Each diamond as the decisions
it has recorded, in the order recorded, with their dates, under the mode the diamond was in when it
took them: discovery until `commit_to_build`, delivery after (DL-1368 S1). Then the decisions still
to come, marked `(next)`. A loop iterates by appending (DL-1373), so a second `start_experiment` is
drawn as its own step where it happened, and the position does not move back. An L0 is not a loop:
it states its purpose (`state_purpose`) and reviews it (`review`). Until v0.309.0 this skill asked
the agent to draw four phases with transition labels of its own; the record has been decisions
since v0.306.0, and the picture is now drawn from them by code.
dora-check
When your agent uses it
Assess delivery health metrics. For software: DORA + APEX. For content/AI/service products: product-type-appropriate metrics.
What it loads into context
Frontmatter
118 tokensAlways available to the agent
SKILL.md
7,235 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Software Products
- Part 1: DORA Metrics (Forsgren)
- Part 2: APEX Metrics (LinearB)
- Part 2b: Compute APEX from raw artifacts (v0.39.19, MANDATORY for software / ai_tool)
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Output
- Part 3: SRE Metrics (Error Budgets)
- Decision Log (MANDATORY)
- Canvas Output
- Part 4: Content Delivery Assessment (v0.11.0)
- Part 5: AI Tool Assessment (v0.11.0)
- Part 6: Service Delivery Assessment (v0.11.0)
- Prior findings first (added v0.96.0)
- Theory Citations
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore29,499 bytes
Read SKILL.md
# Delivery Metrics Check
Assess delivery health using product-type-appropriate metrics. Check `product_type` from `.claude/diamonds/active.yml` to determine which assessment to run.
**Product type routing** (v0.11.0):
- **software**: Full DORA + APEX assessment (Parts 1-3 below)
- **content_course, content_publication, content_media**: Content Delivery Assessment (Part 4 below)
- **ai_tool**: AI Tool Assessment (Part 5 below) + DORA/APEX if code components exist
- **service_offering**: Service Delivery Assessment (Part 6 below)
---
## Preflight: Read target canvas file(s) before any Write/Edit
eval-runner
When your agent uses it
Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
1,061 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Commands
- Result Format
- Pass History
- Creating Scenarios
Files
SKILL.mdcore4,277 bytes
Read SKILL.md
# Eval Runner
Benchmark the agent's performance against defined scenarios. Adapted from n-trax eval system.
## Commands
### `run <category/name>`
1. Read YAML from `.claude/evals/scenarios/<category>/<name>.yml`
2. Parse fields (name, category, task_prompt, success_criteria, budget)
3. Execute setup steps if defined
4. Record start time
5. Execute task via reflexion workflow (read corrections first)
6. Record end time and iteration count
7. Validate ALL success criteriafan-out
When your agent uses it
Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
927 tokensWhen the skill is activated
Reference documents
4,069 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Rules
Files
../../orchestration/agent-teams.mddoc7,830 bytes../../orchestration/leaf-bakeoff.mddoc9,453 bytesSKILL.mdcore3,890 bytes
Read SKILL.md
# Fan-Out / Fan-In Orchestration
## When to Use
- OST has 2+ solutions for the same opportunity that need parallel exploration
- Independent delivery work items that can be parallelized
- Multiple research streams needed simultaneously
## Workflow
### 1. Prepare (Lead Agent)
- Read .claude/canvas/opportunities.yml
- Identify solutions needing parallel work
- For each: identify riskiest assumption, design test, and write its `runs_on` (disk | network | human, as in `/mycelium:assumption-test`)
- Register each `human` test (survey, fake door, interviews, paid pilot) through `/mycelium:handoff`. No subagent runs it: a subagent can only simulate what people would do, and a simulated verdict is not a test result (v0.330.0)feedback-review
When your agent uses it
Aggregate feedback signals across all active loops. Reports health, trajectory, overdue checks, regression warnings, and Goodhart's Law violations.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
2,547 tokensWhen the skill is activated
Reference documents
11,058 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- When to Use
- Workflow
- Output Format
- Canvas Output
- Theory Citations
Scripts executed separately
../../scripts/review_schedule.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/feedback-loops.mddoc23,193 bytes../../scripts/review_schedule.pyruns12,839 bytesSKILL.mdcore10,349 bytesSKILL.mdcore10,349 bytesSKILL.mdcore10,349 bytes
Read SKILL.md
# Feedback Review
Single-place health check across all Mycelium feedback loops. Run periodically or when something feels off.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
framework-health
When your agent uses it
Evaluate Mycelium's own process effectiveness. Measures cycle velocity, discard trends, confidence calibration, gate effectiveness, regression rate. Run quarterly or every 20 cycles.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
6,546 tokensWhen the skill is activated
Reference documents
17,628 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Output
- Rules
- Prior findings first (added v0.96.0)
- Theory Citations
Scripts executed separately
../../scripts/check_retirement_candidates.py../../scripts/mutation_sample.py../../scripts/review_schedule.py
Files
../../engine/adaptive-thresholds.mddoc12,627 bytes../../engine/consistency-check-spec.mddoc34,033 bytes../../harness/design-principles.mddoc14,098 bytes../../harness/theory-tensions.mddoc13,615 bytes../../scripts/check_retirement_candidates.pyruns15,222 bytes../../scripts/mutation_sample.pyruns8,718 bytes../../scripts/review_schedule.pyruns12,839 bytesSKILL.mdcore27,615 bytesSKILL.mdcore27,615 bytesSKILL.mdcore27,615 bytesSKILL.mdcore27,615 bytesSKILL.mdcore27,615 bytes
Read SKILL.md
# Framework Health Check
Mycelium evaluates its own process. This is triple-loop learning — the framework assessing whether it is getting better at producing good outcomes.
## When to Use
- Quarterly review (scheduled)
- After 20 completed leaf cycles (triggered by cycle-history.yml count)
- When process friction is suspected
- Before major framework changes (baseline measurement)
## Workflow
### 1. Load Cycle Datafriction-log
When your agent uses it
Draft a short, honest account of where using Mycelium was confusing or slow, for the user to edit and choose whether to send. Reports experience; never prescribes fixes. Based on Hoskins's friction logging.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
1,442 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- THE ONE RULE THAT MAKES THIS WORK
- WHY THE AGENT DRAFTS IT
- STEP 1 — Draft, from what actually happened this session
- STEP 2 — Add the questions that work at any sample size
- STEP 3 — Hand it over, and only if the user says so
- WHEN TO OFFER THIS
- WHAT THIS IS NOT
Files
SKILL.mdcore6,060 bytes
Read SKILL.md
# Friction Log
**What this is, in Hoskins's words:** *"A friction log is an informal document that you write as you
use a product. You report any confusion or roadblocks you experience. When you've finished, **you
hand it off** to the engineers or PMs responsible for the product."* Its purpose: *"we also need
outside perspectives. Since outsiders don't have all day, we need a lightweight option for them to
help out."*
**Mycelium has the opposite problem from most products: it can see its own friction and has no way to
send it back.** Measured 2026-09-20 in the dogfood repo: of 91 completed outreach tasks, ~71 were
outbound and ~4 inbound. The channel runs one way.
---
gist-plan
When your agent uses it
GIST planning workflow. Structure goals into ideas, steps, and tasks using Gilad's evidence-guided framework.
What it loads into context
Frontmatter
113 tokensAlways available to the agent
SKILL.md
2,305 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Workflow
- Anti-Pattern: The Feature Roadmap
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore9,033 bytesSKILL.mdcore9,033 bytes
Read SKILL.md
# GIST Planning
Replace opinion-based roadmaps with evidence-guided planning. Source: Gilad (Evidence Guided).
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
handoff
When your agent uses it
Generate structured handoff materials for offline human tasks (interviews, observations, outreach). Creates actionable briefs with phone-friendly capture templates.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
3,121 tokensWhen the skill is activated
Reference documents
6,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- When to Use
- Workflow
- Async drip brief (added v0.219.0)
- Canvas Output
- Theory Citations
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytesSKILL.mdcore12,960 bytesSKILL.mdcore12,960 bytesSKILL.mdcore12,960 bytes
Read SKILL.md
# Handoff Skill
Generate structured materials for tasks the human does offline. Bridges the gap between "we need external evidence" and "here's exactly what to do and bring back."
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
harms-check
When your agent uses it
Use when building anything USER-FACING (or with persuasion/retention/cancellation/consent/pricing flows, or that touches vulnerable people) to surface design-level harm the security/privacy/compliance gates miss: dark/deceptive patterns and foreseeable misuse. Assumes the product works as designed and asks who it could harm and whether it is Happier-negative. NUDGE, not a block.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
1,657 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to run (JiT — conditional, NOT universal)
- Workflow
- Output
- Record the verdict on the exposure (v0.321.0)
- Honest limits (scope guard)
- Decision Log (MANDATORY per G-P4)
- Theory Citations
Files
SKILL.mdcore6,967 bytes
Read SKILL.md
# Harms Check Skill
Design-time harm-to-users check — the safety-by-design lens the security/privacy/compliance gates structurally miss. Assumes the product works EXACTLY as designed. `/threat-model` (STRIDE) asks how an attacker breaks it; `/privacy-check` asks about personal data; neither asks: **who could this harm when it works as intended, and how could a legitimate feature be misused?**
This is the design-time front-end of the BVSSH **Happier** dimension: a manipulative or harmful design is Happier-negative by definition, and this gate catches it before `/bvssh-check` would only measure it post-hoc.
## When to run (JiT — conditional, NOT universal)
Fires only when the product-shape warrants it:
- **User-facing** product/feature (real people use it), OR
- has **persuasion / retention / conversion / cancellation / consent / pricing** flows (the dark-pattern surface), OR
- **touches vulnerable people** (children, patients, financially- or otherwise at-risk).
If none apply (internal dev tooling, a library, a build script), **SKIP — say so and move on.** This is a NUDGE, never a hard block.ice-score
When your agent uses it
Use to prioritize solutions or opportunities using ICE scoring with evidence-backed confidence.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
8,808 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Which ICE this is
- Workflow
- Rules
- Canvas Output
- Theory Citations
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore34,616 bytesSKILL.mdcore34,616 bytes
Read SKILL.md
# ICE Score Skill
ICE scoring as Itamar Gilad defines it: Impact x Confidence x Ease, each 0-10, with Confidence taken from his Confidence Meter.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
interview
When your agent uses it
Use when onboarding a new product/project. Progressive interview to understand purpose, vision, north star, and competitive landscape.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
12,793 tokensWhen the skill is activated
Reference documents
17,798 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First: are Mycelium's hooks running here? (v0.286.0)
- Preflight: Read target canvas file(s) before any Write/Edit
- When to Use
- Workflow
- Evidence Classification
- Output
- Phase 6: Project Classification (NEW in v0.2)
- After the Interview: What Happens Next
- Theory Citations
- Handling User-Supplied Content
- Confidence-math: canvas-density-emergent (partial — depth additions still pending)
Scripts executed separately
../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/canvas-guidance.ymlasset56,574 bytes../../engine/confidence-thresholds.ymlasset24,591 bytes../../engine/dogfood-mode.mddoc4,659 bytes../../engine/wayfinding.mddoc7,445 bytes../../jit-tooling/metrics-adapters/GENERATING.mddoc7,004 bytes../../jit-tooling/metrics-detector.mddoc9,063 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../define-done/SKILL.mddoc21,566 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytesSKILL.mdcore52,807 bytes
Read SKILL.md
# Interview Skill
## First: are Mycelium's hooks running here? (v0.286.0)
Run `find .claude/state/hooks-alive "${TMPDIR:-/tmp}/mycelium-hooks-alive-$(id -u)" -mmin -60 2>/dev/null`. If it prints a path (since v0.318.0 the hooks also stamp the temp folder in a project with no Mycelium state yet, where they do nothing else), say nothing
about it and go on. If it prints nothing, Mycelium's hooks did not run in this session: its gates
and the rules it gives the agent at session start are off, and nothing else will say so. Tell the
user in one line before anything else: "Mycelium's hooks are not running in this session, so its
gates are off. On Codex CLI, open `/hooks`, trust Mycelium's hooks and start a new session; on
Claude Code, check the plugin is enabled in `/plugin`." Then carry on with this skill.
Progressive onboarding through structured discovery conversation.
## Preflight: Read target canvas file(s) before any Write/Editjtbd-map
When your agent uses it
Map the Jobs to be Done (functional, emotional, and social) that people are trying to get done. Based on Christensen's JTBD theory — applies to any object, not only software.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
1,524 tokensWhen the skill is activated
Reference documents
6,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Job Statement Format
- Three Dimensions (all required)
- Discovery Process
- Output
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytesSKILL.mdcore6,208 bytes
Read SKILL.md
# Jobs to be Done Mapping
People "hire" products to get jobs done. Map ALL three dimensions. Source: Christensen.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
launch-tier
When your agent uses it
Classify releases into launch tiers and plan go-to-market. Based on Lauchengco's Loved framework.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
5,859 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Tier Definitions — AN EXAMPLE CALIBRATION, NOT THE SCALE
- Classification Criteria
- The categorisation SPAWNS AN L5 — do this before the per-tier activities (v0.232.0)
- Per-Tier Activities
- Behavioral Science in Positioning (Shotton)
- Canvas Output
- Ethical Engagement Design (Eyal -- Hook Model + Indistractable)
- Pre-Launch Bias Check
- After Launch: The L5 -> L2 Feedback Loop
- Cycle History Recording
- Decision Log (MANDATORY per G-P4)
- Theory Citations
- Counter-Argument Check (Bias Mitigation)
- Postflight: Verify-After-Write (claim matches state)
Scripts executed separately
../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore24,080 bytesSKILL.mdcore24,080 bytes
Read SKILL.md
# Launch Tier Classification
**The instrument is Lauchengco's RELEASE SCALE, and this skill had it wrong until 2026-09-20.**
Corrected after reading *LOVED* chapter 12 directly. What the book actually says:
> *"Developing a shared understanding of how a release should be categorized and what go-to-market
> activities will get done is the purpose of a Release Scale. It's a simple tool whose **sole purpose
> is to create shared vocabulary and expectations** between the product and go-to-market teams."*
> *"**This is different from a detailed organizational plan** for every action needed for a product
> launch."*
**Three consequences for how this skill is used.**
1. **THE SCALE IS BUILT, NOT ADOPTED.** Her step 1: *"Decide on the calibration scale. **Be itlog-evidence
When your agent uses it
Record findings from completed offline human tasks (interviews, observations, outreach) back into the canvas. The re-entry point after /mycelium:handoff.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
4,913 tokensWhen the skill is activated
Reference documents
8,953 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- When to Use
- Workflow
- Canvas Output
- Theory Citations
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytes../../engine/status-translations.mddoc9,460 bytesSKILL.mdcore20,930 bytesSKILL.mdcore20,930 bytesSKILL.mdcore20,930 bytesSKILL.mdcore20,930 bytesSKILL.mdcore20,930 bytesSKILL.mdcore20,930 bytes
Read SKILL.md
# Log Evidence Skill
The re-entry point after offline human work. Takes raw conversation notes, observations, or survey results and integrates them into the canvas with proper provenance.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
metrics-detect
When your agent uses it
Detect which external metric sources apply to this product (GitHub, Plausible, Stripe, etc.) and configure adapters. Retrofit entry point for projects that started before v0.14; also runnable to refresh source list when the product grows.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
835 tokensWhen the skill is activated
Reference documents
4,029 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Credentials
- Output
- What This Skill Does NOT Do
- Theory Citations
Files
../../jit-tooling/metrics-adapters/GENERATING.mddoc7,004 bytes../../jit-tooling/metrics-detector.mddoc9,063 bytesSKILL.mdcore3,574 bytesSKILL.mdcore3,574 bytesSKILL.mdcore3,574 bytesSKILL.mdcore3,574 bytesSKILL.mdcore3,574 bytes
Read SKILL.md
# Metrics Detect Skill
Retrofit entry point for `${CLAUDE_PLUGIN_ROOT}/jit-tooling/metrics-detector.md`. For new projects this runs automatically inside `/mycelium:interview` Phase 6. Use this skill when:
- The project existed before v0.14 and has no `.claude/jit-tooling/active-metrics.yml`.
- New infrastructure has been added (new analytics provider, new app store, new payment processor) and source list needs refresh.
- An existing adapter is >180 days old and needs regeneration.
- The user explicitly wants to review / reconfigure metric sources.
## Workflow
Follow `${CLAUDE_PLUGIN_ROOT}/jit-tooling/metrics-detector.md` end-to-end:
1. **Signal scan** — check git remote, package manifests, env vars, SDK installs.metrics-pull
When your agent uses it
Pull snapshots from all configured metric sources, compute deltas against prior snapshots, flag unexplained signals, and draft evidence entries for canvas files. One entry point for all external product/market metrics.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
3,971 tokensWhen the skill is activated
Reference documents
5,045 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Precondition: .claude/jit-tooling/active-metrics.yml exists
- Workflow
- Parallel dispatch
- Partial success behavior
- Idempotency
- What NOT to Do
- Output
- Theory Citations
Files
../../engine/reading-for-meaning.mddoc4,338 bytes../../jit-tooling/metrics-adapters/GENERATING.mddoc7,004 bytes../../jit-tooling/metrics-detector.mddoc9,063 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytesSKILL.mdcore16,986 bytes
Read SKILL.md
# Metrics Pull Skill
Unified pull across all metric sources configured in `.claude/jit-tooling/active-metrics.yml`. Dispatches to per-source adapters (starting with `github`), normalizes to a shared schema, computes deltas, and drafts canvas evidence entries.
This skill is the L0/L1/L2/L5 evidence-gathering loop. Replaces manual "I checked the dashboard" reports with timestamped, sourced, diffable data.
## When to Use
- Before `/mycelium:diamond-assess` at L0/L1/L2/L5, if the newest snapshot is >7 days old.
- After any public activity (launch, post, conference mention) — typically 24-48h later to capture the bump.
- Weekly baseline, regardless of activity.
- Ad hoc when the user wants a fresh read.
## Precondition: .claude/jit-tooling/active-metrics.yml existsmigrate-from-legacy
When your agent uses it
Migrate a Mycelium project from legacy install (npx-degit, framework files in .claude/) to plugin install (framework lives in plugin cache, .claude/ holds project state only). Detects current install form, walks the user through plugin installation, runs the migration script, and verifies project state survived. Idempotent — safe to invoke on already-migrated projects.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
2,823 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Detect current install form
- Step 2: Verify the plugin is installed
- Step 3: Verify a clean working tree
- Step 4: Show the user what will happen
- Step 5: Run the migration script
- Step 6: Verify project state survived
- Step 7: Settings hooks block (manual cleanup)
- Step 8: Final commit
- Idempotency
- What this skill does NOT do
- Theory grounding
- Source
- Handling User-Supplied Content
Files
../../hooks/hooks.jsonasset20,541 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytesSKILL.mdcore11,663 bytes
Read SKILL.md
# Migrate from legacy to plugin form
When this skill runs, walk the user through moving from legacy install to plugin install. The migration is **non-destructive** to project state: canvas, diamonds, memory, decision log, evals, and active metrics are preserved. Only framework reference content (skills, hooks, engine, scripts, schemas, etc.) is removed from `.claude/` — that content now ships in the plugin cache.
## Step 1: Detect current install form
Check the project's `.claude/` directory:
```bash
test -d "${CLAUDE_PROJECT_DIR:-.}/.claude/skills" && echo "legacy framework files present" || echo "no legacy framework files"
test -d "${CLAUDE_PROJECT_DIR:-.}/.claude/canvas" && echo "project state present" || echo "no project state"
```
Three states:mocked-persona-interview
When your agent uses it
Use when real user interviews aren't possible (solo/hobby/dogfood projects) but persona work is still needed. Enforces epistemic discipline: adversarial spectrum, pre-committed stop conditions, speculation tagging. NOT a substitute for /mycelium:user-interview when real users are available.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
3,921 tokensWhen the skill is activated
Reference documents
9,643 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Why This Skill Exists
- Discipline Rules (Non-Negotiable)
- Workflow
- Output Format
- Anti-Patterns This Skill Prevents
- Canvas Output
- Theory Citations
- Related Skills
- Honest Caveat
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/autonomous-mode.mddoc16,821 bytesSKILL.mdcore16,962 bytesSKILL.mdcore16,962 bytesSKILL.mdcore16,962 bytes
Read SKILL.md
# Mocked Persona Interview Skill
A disciplined alternative to real user interviews when:
- You're a solo developer and cannot talk to users this week
- You're on a hobby/learning project with no user research budget
- You're running a meta-project dogfood session (see `dogfood_modifier`)
- You're in early L0/L1 exploration where real interviews are premature
**This skill is NOT a substitute for `/mycelium:user-interview` when real users are available.** Mocked personas are simulation. They catch some mistakes, miss others, and — without discipline — become a confirmation-bias machine. This skill's job is to enforce the discipline.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
ost-builder
When your agent uses it
Use to build or update an Opportunity Solution Tree from research data. Never from brainstorming.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
4,540 tokensWhen the skill is activated
Reference documents
8,301 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Workflow
- Purpose stance on every solution (v0.120.0)
- Rules
- Output to the user
- Canvas Output
- Lean UX Connection
- Theory Citations
- Handling User-Supplied Content
Scripts executed separately
../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/cynefin-routing.mddoc7,087 bytes../../engine/reading-for-meaning.mddoc4,338 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore19,106 bytesSKILL.mdcore19,106 bytesSKILL.mdcore19,106 bytesSKILL.mdcore19,106 bytesSKILL.mdcore19,106 bytesSKILL.mdcore19,106 bytesSKILL.mdcore19,106 bytes
Read SKILL.md
# OST Builder Skill
Build and maintain Opportunity Solution Trees from research evidence.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
ost-render
When your agent uses it
Render `.claude/canvas/opportunities.yml` as a diagram or structured list. Read-only. Default format Mermaid mindmap. Consults the attribution registry per `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` consent + privacy gate. Second specialist in the render fleet.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
4,177 tokensWhen the skill is activated
Reference documents
5,397 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When NOT to use
- Identifier exposure
- Preflight: Read sources
- Arguments
- Workflow
- Rules
- Counter-Argument Check
- What this skill does NOT do
- Test fixtures (G-V12 / Check 37)
- Theory citations
Scripts executed separately
../../scripts/validate_mermaid.py
Files
../../engine/render-conventions.mddoc22,944 bytes../../scripts/validate_mermaid.pyruns7,553 bytesSKILL.mdcore16,441 bytesSKILL.mdcore16,441 bytesSKILL.mdcore16,441 bytesSKILL.mdcore16,441 bytes
Read SKILL.md
# OST Render
Read-only render of `.claude/canvas/opportunities.yml` as a diagram or structured list. Second specialist in the render fleet (after `/mycelium:diamond-render`). See `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` for shared conventions.
## When NOT to use
- To BUILD or update the OST from research data → `/mycelium:ost-builder`. This skill is read-only.
- For cross-cutting opportunity→solution→cycle traceability view → dispatcher's `/mycelium:render --view traceability` (deferred to Phase 4a–4d research-first methodology per architecture draft §10.2).
- For ICE scoring of solutions → `/mycelium:ice-score`.
## Identifier exposure
**Declared**: YES
ping
When your agent uses it
Smoke-test skill that confirms the Mycelium plugin loaded correctly. Returns a deterministic marker string for plugin-shape validation. Not for end-user invocation in normal use.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
280 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore1,242 bytes
Read SKILL.md
# Ping (smoke-test only)
When invoked, respond with exactly this single line and nothing else:
```
MYCELIUM_PLUGIN_LOAD_OK
```
This is a plugin-shape marker, not a version assertion — it confirms the plugin packaging works end-to-end (manifest → marketplace → install → namespaced invocation). The version a user is actually running comes from `/plugin list` or `plugin.json#version`, not this marker. (The marker was previously version-suffixed, which created drift: it stayed pinned at `_v0.20.0` while plugin.json moved through 10 patches. Detected during 2026-05-09 dogfood.)
For real Mycelium skills, see the parent `skills/` directory once migration completes.preflight
When your agent uses it
Use before starting delivery work. Pre-implementation validation checklist to ensure readiness.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,928 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Checklist
- Before anything meets real people (v0.246.0)
- If Every Item Passes: offer the L4 cycle (v0.243.0)
- If Any Item Fails
- Theory Citations
Scripts executed separately
../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore8,168 bytes
Read SKILL.md
# Preflight Skill
Pre-delivery validation checklist. Run before every implementation task.
## Checklist
### Constraints (ALWAYS FIRST)
Before scoping any delivery work, establish constraints. Do not propose a plan before knowing the budget.
- [ ] **Time budget**: "How much time do you have for this?" (hours, days, sprint length)
- [ ] **Resource constraints**: Solo? Team? What skills are available?
- [ ] **Fidelity**: Demo/prototype vs. production? Who is the audience?
- [ ] **Dependencies**: Waiting on anything external?privacy-check
When your agent uses it
Use to assess Privacy by Design compliance and GDPR/data protection alignment for a feature or system.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
1,710 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Canvas (MANDATORY — the source of truth, do this FIRST)
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Decision Log (MANDATORY per G-P4)
- Theory Citations
Files
SKILL.mdcore7,194 bytesSKILL.mdcore7,194 bytes
Read SKILL.md
# Privacy Check Skill
Privacy by Design assessment.
## Workflow
### 7 Foundational Principles (Cavoukian)
1. **Proactive not Reactive**: Are privacy measures built in from the start?
- [ ] Privacy considered in design phase, not bolted on
- [ ] Risks identified before implementation
2. **Privacy as Default**: Is the most private option the default?
- [ ] Data collection opt-in, not opt-outprompt-optimizer
When your agent uses it
A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
527 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Commands
- Workflow
Files
SKILL.mdcore2,186 bytes
Read SKILL.md
# Prompt Optimizer
Systematically improve Mycelium instructions through measurement. Adapted from n-trax.
## Commands
### `baseline` -- Capture current performance
1. Run `/mycelium:eval-runner run-split optimization` — record as optimization scores
2. Run `/mycelium:eval-runner run-split holdout` — record as holdout scores
3. Record both to `.claude/optimization/baseline.json`: timestamp, CLAUDE.md hash, optimization metrics, holdout metrics, overall and per-category metrics
### `test <variant>` -- Test a variant
1. Read variant from `.claude/optimization/variants/<variant>.md`
2. Apply the CLAUDE.md changes describedpurpose-properties
When your agent uses it
Derive the binding properties your why/how/what impose on everything below them, so no solution can silently contradict your own product definition. Retrofit entry point for projects that started before v0.120.0; also the re-derive path when why/how/what change and every stance below them goes stale.
What it loads into context
Frontmatter
152 tokensAlways available to the agent
SKILL.md
3,338 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Read the current state and say which case this is
- Step 2: Attempt extraction, and classify what fails
- Step 2a: Screen for quality adjectives BEFORE trusting your own refusal
- Step 2b: Check the ALTITUDE of every candidate before you record it
- Step 3: Interview the builder on what failed — with candidates, not an open question
- Step 4: The user marks `binding`, and only they can
- Step 5: Write, then say what changed downstream
- What this skill does NOT do
- Step 6: Offer the BEARING, and take "no" for an answer (v0.230.0)
- Theory grounding
Scripts executed separately
../../scripts/check_purpose_stance.py
Files
../../scripts/check_purpose_stance.pyruns35,897 bytesSKILL.mdcore14,253 bytesSKILL.mdcore14,253 bytes
Read SKILL.md
# Purpose Properties Skill
Retrofit and re-derive entry point for `purpose.yml#purpose_properties`. **For new projects this runs
inside `/mycelium:start` Step 3b.** Use this skill when:
- The project existed before **v0.120.0** and has no `purpose_properties` (the retrofit case — every
project created before that release, since `/mycelium:start` Step 4 exits for already-initialized
projects and never reaches the extraction).
- `why`, `how` or `what` changed, so `derived_from_hash` no longer matches and **every stance below
it is superseded** (the drift case — this is the one that matters most and the easiest to skip).
- A property list exists but the user wants to revisit which properties are `binding`.
Full contract: https://github.com/haabe/mycelium/blob/main/docs/purpose-stance.md (it lives in the repository, not in the installed plugin).
receipt-render
When your agent uses it
Render a completed diamond's work as a shareable, factual one-page "work receipt" (problem framed, assumptions tested, what was killed vs kept) carrying an origin line + a volitional onward-handoff data flow. Read-only. Consults the attribution registry per `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` consent + privacy gate. Follows the render fleet's shared conventions + consent gate (Check 43 applies via the `-render` name); a standalone shareable-artifact generator, NOT a `/render` dispatcher target. Audience fixed `external` (a hand-it-over artifact).
What it loads into context
Frontmatter
244 tokensAlways available to the agent
SKILL.md
3,390 tokensWhen the skill is activated
Reference documents
5,397 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists (the honest framing)
- When NOT to use
- Identifier exposure
- Preflight: Read sources
- Arguments
- Workflow
- Rules
- Counter-Argument Check
- What this skill does NOT do
- Test fixtures (G-V12 / Check 43)
- Theory citations
Files
../../engine/render-conventions.mddoc22,944 bytesSKILL.mdcore14,292 bytesSKILL.mdcore14,292 bytesSKILL.mdcore14,292 bytesSKILL.mdcore14,292 bytesSKILL.mdcore14,292 bytes
Read SKILL.md
# Receipt Render
Read-only render of a **completed diamond** as a shareable, factual one-page **work receipt** — the problem as it was framed, the assumptions tested, what was killed and what was kept. It follows the render fleet's shared conventions and consent gate (`${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md`; Check 43 applies via the `-render` name), but unlike the diagram specialists (`diamond-render` / `ost-render` / `cycle-render`) it produces a shareable prose artifact and is **not** a `/mycelium:render` dispatcher target.
The receipt is a **carrier the user may choose to hand to a colleague**. It is generated fully **locally** — nothing is transmitted. Its footer carries a volitional data flow (an origin line + a pre-filled GitHub Discussion deep-link) so that, *if the user chooses*, the work can surface back to the maintainer. The skill never posts anything; a human reviews a draft and submits it.
## Why this exists (the honest framing)
A silent adopter is invisible to a solo maintainer. This skill does not generate adoption and does not phone home. It gives a real piece of completed work a shareable shape with a low-friction, non-leading way for the user (or a colleague they hand it to) to surface themselves — if they want to. It surfaces **behaviour** (what was built), never solicits **praise** (whether it was good).
## When NOT to use
- To render a diamond's *state* as a diagram → `/mycelium:diamond-render`. This skill renders *completed work as prose*, not a state machine.
- For an in-progress diamond → this skill refuses (a receipt summarizes finished work; see Rules). Run it after the diamond records `close`.reflexion
When your agent uses it
Use for self-correcting implementation. Implements the reflexion loop: implement, validate, self-critique, retry (max 3 iterations).
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
1,269 tokensWhen the skill is activated
Reference documents
3,273 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Verification Modes
- Rules
- Theory Citations
Files
../../engine/canvas-guidance.ymlasset56,574 bytes../../harness/engineering-principles.mddoc15,680 bytesSKILL.mdcore5,582 bytesSKILL.mdcore5,582 bytes
Read SKILL.md
# Reflexion Skill
Self-correcting implementation loop from the n-trax pattern.
## Workflow
### Iteration Loop (max 3)
**Step 1: Implement**
- Create the deliverable according to the specification/acceptance criteria.
- Software: write code. Content: write/produce content. AI tool: write prompts/configs. Service: document workflow.
- Follow ${CLAUDE_PLUGIN_ROOT}/harness/engineering-principles.md (principles apply to all product types).
- Apply patterns from patterns.md.
- Check corrections.md for relevant past mistakes.regulatory-review
When your agent uses it
Use to assess regulatory applicability for products that may fall under AI regulation (EU AI Act, Article 50 transparency).
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
1,793 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- When to Use
- Workflow
- Output Format
- Important Disclaimer
- Theory Citations
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore7,397 bytes
Read SKILL.md
# Regulatory Review Skill
Assess whether the product falls under AI regulation and identify compliance requirements.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
render
When your agent uses it
Central dispatcher for the canvas/state render fleet. Routes intent to a specialist (`/mycelium:diamond-render`, `/mycelium:ost-render`, `/mycelium:cycle-render`) OR lists what's renderable. Cross-cutting views spanning multiple canvases (opp→sol→cycle traceability, confidence-over-time, cluster-graduation-flow) are research-gated and NOT emitted by default. See `${CLAUDE_PLUGIN_ROOT}/engine/render-conventions.md` for shared conventions.
What it loads into context
Frontmatter
165 tokensAlways available to the agent
SKILL.md
2,446 tokensWhen the skill is activated
Reference documents
5,397 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- When NOT to use
- Identifier exposure
- Arguments
- Workflow
- Rules
- Counter-Argument Check
- What this skill does NOT do
- Theory citations
Files
../../engine/render-conventions.mddoc22,944 bytesSKILL.mdcore10,358 bytesSKILL.mdcore10,358 bytes
Read SKILL.md
# Render Dispatcher
Central entry point + menu for the canvas/state render fleet. Routes intent to specialists or surfaces what's available. Cross-cutting views are research-gated and NOT emitted by default. Completes the v0.40.0-announced render fleet foundation.
## When to use
- "Show me the OST" / "render the diamond state" / "visualize the cycles" → dispatcher recommends + routes to the specialist (recommend, do NOT auto-invoke).
- "Visualize how opportunity X became cycle Y" → cross-cutting traceability intent. Dispatcher surfaces that the view is research-gated; does not emit a default rendering.
- Discovery: "what renderable views does Mycelium have?" → dispatcher lists specialists + their states.
## When NOT to use
- If the user names a specialist directly (`/mycelium:diamond-render`, `/mycelium:ost-render`, `/mycelium:cycle-render`), the specialist is the one-hop path. Do NOT re-route through the dispatcher.
- For cross-cutting views that already have dedicated skills (e.g., `/mycelium:framework-health` is its own audit; not a render specialist).retrospective
When your agent uses it
Structured retrospective after completing a delivery increment or diamond. Captures learning for continuous improvement.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
5,479 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Workflow
- Root Cause Analysis (when "What Didn't Go Well" surfaces a significant problem)
- Blameless Post-Mortem Format (SRE)
- Refactoring Prompt
- Output
- The doctrine retrospective, and its firing condition (v0.230.0)
- Counter-Argument Check (Bias Mitigation)
- Postflight: Verify-After-Write (claim matches state)
Scripts executed separately
../../scripts/check_doctrine_due.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../scripts/check_doctrine_due.pyruns5,799 bytesSKILL.mdcore22,913 bytesSKILL.mdcore22,913 bytes
Read SKILL.md
# Retrospective
Run after every completed **cycle**: a solution leaf reaching a terminal state (launched, archived, killed), or a framework-development arc that shipped. Not only after a diamond completes — a diamond at L0 to L2 can stay open for months while cycles close under it weekly. Measured on the dogfood repo (2026-08-30): 17 cycles in 116 days, median 3.5 days apart, while every diamond stayed open the whole time; the earlier wording ("after every completed delivery diamond or significant milestone") named two units forty times apart and the load-bearing one was the vague one. Source: Forsgren (learning culture).
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
scaffold-cost-check
When your agent uses it
Measure Mycelium's own scaffold token cost (CLAUDE.md + engine + harness + canvas + memory) and surface a structured estimate. One-shot audit; pair with /framework-health for trend tracking.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
1,612 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Preflight: Read target canvas file(s) before any Write/Edit
- Workflow
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Output
- Canvas Output (only if `--write`)
- Decision Log (MANDATORY if `--write`)
- Wiring
- Rules
- Theory Citations
Files
SKILL.mdcore6,371 bytes
Read SKILL.md
# Scaffold Cost Check
Measure the token cost of Mycelium's stable scaffolding — the context surface loaded at SessionStart and on routine canvas/memory reads — so claims about "negligible overhead" are auditable. Datadog's *State of AI Engineering* (2026) reports ~69% of input tokens across production agents are system prompts; this skill makes Mycelium's analogous number visible.
## When to Use
- First-time audit on a project to compare actual scaffold cost against any "~6K negligible" claim in landscape/positioning.
- Periodic refresh via `/mycelium:framework-health` (see Wiring below).
- Before adding a new canvas file or harness doc that joins the stable load surface, to surface the marginal cost.
## Preflight: Read target canvas file(s) before any Write/Edit
Hard rule. Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. This skill only WRITES if explicitly asked to persist its output to `dora-metrics.yml#apex.scaffold_token_estimate`; default behavior is print-only.
security-review
When your agent uses it
OWASP secure design review for code and architecture. Checks input validation, authentication, authorization, data protection.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
2,851 tokensWhen the skill is activated
Reference documents
492 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 0: Scope the review to what the product holds and does (v0.271.0)
- Checklist (OWASP Top 10:2025, applies when `runs_code`)
- OWASP Top 10 for LLM Applications (2025)
- OWASP Agentic Skills Top 10 (AST10)
- Decision Log (MANDATORY per G-P4)
- Stack-Specific Tools
- NUDGE-AT-FAILURE (4-layer JIT composition)
- Handling User-Supplied Content
Files
../../jit-tooling/security-scanning.mddoc1,888 bytesSKILL.mdcore12,076 bytesSKILL.mdcore12,076 bytesSKILL.mdcore12,076 bytesSKILL.mdcore12,076 bytesSKILL.mdcore12,076 bytes
Read SKILL.md
# Security Review
Language-agnostic security review based on OWASP Secure by Design.
## Step 0: Scope the review to what the product holds and does (v0.271.0)
**Record the scope first, then apply only the sections it calls for.** Every product has threats,
but not every product has a login, code, or personal data. Founder, 2026-09-26: "2fa and so on
might not be applicable for all products." A bookkeeping service delivered by hand was reviewed
against this web checklist (CORS, SQL parameters, security headers, multi-factor login), most of
which has nothing to act on there. Write in `.claude/canvas/threat-model.yml`, under its own key
(`scope` stays the threat model's own sentence on what is being modelled; 0.271.0 reused that name and
broke every threat model that had one):
service-check
When your agent uses it
Use to evaluate a service or feature against Downe's 15 principles of good services.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
1,929 tokensWhen the skill is activated
Reference documents
10,585 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Checklist
- When to Run
- Output
- Canvas (MANDATORY — the source of truth, do this FIRST)
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Decision Log (MANDATORY per G-P4)
- Theory Citations
Files
../../harness/anti-patterns.mddoc47,849 bytesSKILL.mdcore7,762 bytesSKILL.mdcore7,762 bytes
Read SKILL.md
# Service Check Skill
Evaluate against Lou Downe's 15 principles.
## Checklist
For each principle, assess: Pass / Partial / Fail / N/A
1. **Easy to find**: Can users find this service without knowing its name?
- [ ] Discoverable through natural search terms
- [ ] Linked from logical starting points
2. **Clearly explains its purpose**: Is it immediately clear what this does?
- [ ] Purpose statement visible without scrollingsetup
When your agent uses it
First-run setup for the Mycelium plugin. Creates project-state directories (.claude/canvas, .claude/diamonds, .claude/memory, .claude/harness) and minimal starter files in the user's project. Optionally provisions opencode runtime support (a starter scaffold) when opencode is detected or requested, and declares the gates in .vibe/hooks.toml when Mistral Vibe is. Idempotent — re-running on an initialized project is a no-op. Run this once after installing the Mycelium plugin and before invoking other skills.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
7,154 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First: are Mycelium's hooks running here? (v0.286.0)
- Then: can the gates read the canvas? (v0.290.0)
- Step 1: Detect initialization state
- Step 2: Create project-state directory structure
- Step 3: Write minimal starter files
- Step 4: Optionally write AGENTS.md at project root
- Step 5: Optionally provision opencode runtime support
- Step 5v: Optionally declare the gates for Mistral Vibe (v0.332.0)
- Before the confirmation: offer the secret scan for commits made by hand (v0.323.0)
- Step 6: Confirmation message
- What this skill does NOT do
- Theory grounding
- Source
- Handling User-Supplied Content
Scripts executed separately
../../scripts/_state_dir.py../../scripts/install_git_secret_hook.py../../scripts/install_git_secret_hook.py../../scripts/migrate_phase.py
Files
../../harness/do-not-cite.ymlasset4,203 bytes../../scripts/_state_dir.pyruns8,058 bytes../../scripts/install_git_secret_hook.pyruns3,903 bytes../../scripts/install_git_secret_hook.pyruns3,903 bytes../../scripts/migrate_phase.pyruns13,212 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytesSKILL.mdcore28,906 bytes
Read SKILL.md
# Mycelium plugin setup
## First: are Mycelium's hooks running here? (v0.286.0)
Run `find .claude/state/hooks-alive "${TMPDIR:-/tmp}/mycelium-hooks-alive-$(id -u)" -mmin -60 2>/dev/null`. If it prints a path (since v0.318.0 the hooks also stamp the temp folder in a project with no Mycelium state yet, where they do nothing else), say nothing
about it and go on. If it prints nothing, Mycelium's hooks did not run in this session: its gates
and the rules it gives the agent at session start are off, and nothing else will say so. Tell the
user in one line before anything else: "Mycelium's hooks are not running in this session, so its
gates are off. On Codex CLI, open `/hooks`, trust Mycelium's hooks and start a new session; on
Claude Code, check the plugin is enabled in `/plugin`." Then carry on with this skill.
When this skill runs, do the following sequence. The skill is designed to be safe to re-run — every step is idempotent.
## Then: can the gates read the canvas? (v0.290.0)start
When your agent uses it
One command from "plugin installed" to "running brief on your idea." Combines /mycelium:setup (project-state initialization) and /mycelium:interview (10-minute discovery brief) into a single flow. Run this immediately after installing the Mycelium plugin — it's the recommended entry point for first-time users.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
3,004 tokensWhen the skill is activated
Reference documents
19,947 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Welcome (~30 seconds of context, then move on)
- Step 2: Detect existing state — HARD GATE
- Step 3: Run interview (universal-flow shape)
- Step 3b: Derive purpose properties (immediately after why/how/what land)
- Step 4: Routing for already-initialized projects
- What this skill does NOT do
- Why this skill exists
- Theory grounding
- Source
Files
../interview/SKILL.mddoc52,807 bytes../setup/SKILL.mddoc28,906 bytesSKILL.mdcore12,469 bytesSKILL.mdcore12,469 bytes
Read SKILL.md
# /mycelium:start — combined first-time entry
When this skill runs, follow the flow below. The skill is designed so a first-time user goes from "plugin installed" to "holding a one-page brief on their idea" in a single invocation.
## Step 1: Welcome (~30 seconds of context, then move on)
Output a short welcome before doing anything. Do NOT skip this — the install-to-here gap is the friction point this skill exists to address. The user just installed a 45-skill framework and has no context yet.
> "Welcome to Mycelium.
>
> Mycelium makes the agent think before it builds — it can't skip the hard questions; each step has to clear an evidence check first. Grounded in 30+ established product-thinking frameworks; you'll meet the relevant ones as they come up.
>
> Two quick steps:
> 1. Set up Mycelium's files in `.claude/` — about 10 seconds. Your existing files (CLAUDE.md, README, etc.) aren't changed. A new `.claude/` directory is added, and setup may add an `AGENTS.md` at the project root (it asks first when you are there to answer).team-shape
When your agent uses it
Assess team structure against Skelton's Team Topologies. Evaluate cognitive load, interaction modes, and Conway's Law alignment.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
2,597 tokensWhen the skill is activated
Reference documents
5,841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Assessment Workflow
- Bounded Agency (Skelton, 2025-2026)
- Output
- Postflight: Verify-After-Write (claim matches state)
Files
../../engine/agent-operating-contract.mddoc24,482 bytesSKILL.mdcore11,061 bytesSKILL.mdcore11,061 bytes
Read SKILL.md
# Team Shape Assessment
Evaluate organizational design for fast flow. Source: Skelton & Pais, *Team Topologies*,
**2nd edition (IT Revolution, 23 Sept 2025, ISBN 9781966280002)**.
**Model re-verified against primary sources 2026-09-01** — teamtopologies.com/key-concepts, the
2nd-edition publisher page, and the 2026 AI material (QCon London keynote 17 Mar 2026; "AI ROI"
executive report 12 Aug 2026). It is still **four** fundamental team types and **three**
interaction modes. The authors have added no AI-specific team type, and their stated position is
that none is needed. Third parties do propose new ones (SAFe, various blogs) and InfoQ's QCon
report names an "Innovation and Practices Enabling Team" — read the name: that is a *named
specialization of the existing enabling team*, not a fifth fundamental type. Do not add either to
the enum in `schemas/canvas/team-shape.schema.json`.
theory-fidelity
When your agent uses it
Audit whether the theories/methodologies a project claims to implement are faithfully operationalized — or name-dropped, partially built, distorted, or over-claimed. Source-grounds the load-bearing theories; tags the rest provisional. Run periodically alongside /framework-health.
What it loads into context
Frontmatter
160 tokensAlways available to the agent
SKILL.md
3,919 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- The Grading Rubric (five axes)
- Workflow
- Output Format
- Rules
- Theory Citations
Scripts executed separately
../../scripts/check_primary_theory_gated.py../../scripts/review_schedule.py
Files
../../scripts/check_primary_theory_gated.pyruns7,951 bytes../../scripts/review_schedule.pyruns12,839 bytesSKILL.mdcore16,582 bytesSKILL.mdcore16,582 bytesSKILL.mdcore16,582 bytesSKILL.mdcore16,582 bytesSKILL.mdcore16,582 bytes
Read SKILL.md
# Theory Fidelity Audit
Most framework checks evaluate *process* (cycle health, gates) or *artifact performance* (evals, DORA). None of them ask the question this skill exists for: **for every theory a project claims to represent, is the mapped mechanism actually faithful to what the theory says — or is it theatre?** This is the audit of the theory→mechanism mapping itself.
The framework's own stated bar (`docs/theories.md`): *"every theory is mechanism-mapped … citations without mechanism-mapping are theatre."* This skill holds the project to that bar — including holding the theory doc to it.
## When to Use
- Quarterly, alongside `/mycelium:framework-health` (process health) — this is the theory-fidelity half.
- After adding/citing a new theory, or after editing a theory's mechanism (skill/gate/schema).
- When a citation looks decorative, or when a doc claims a mechanism you suspect doesn't exist.
## The Grading Rubric (five axes)
threat-model
When your agent uses it
Use to conduct STRIDE threat modeling for a system or feature design.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
2,659 tokensWhen the skill is activated
Reference documents
3,244 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- OWASP Top 10 for LLM Applications (2025)
- OWASP Agentic Skills Top 10 (AST10)
- Canvas (MANDATORY — the source of truth, do this FIRST)
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Decision Log (MANDATORY per G-P4)
- Theory Citations
- Handling User-Supplied Content
Files
../../harness/security-trust.mddoc15,263 bytesSKILL.mdcore11,396 bytesSKILL.mdcore11,396 bytesSKILL.mdcore11,396 bytes
Read SKILL.md
# Threat Model Skill
STRIDE threat modeling for secure design.
## Workflow
1. **Define scope**: What system/feature/component is being modeled?
2. **Draw data flow diagram** (textual):
- Identify actors (users, external systems)
- Identify processes (services, functions)
- Identify data stores (databases, caches, files)
- Identify data flows (what moves between components)
- Identify trust boundaries (where trust level changes)usability-check
When your agent uses it
Evaluate user-facing interfaces against Nielsen's 10 Usability Heuristics. Complements /mycelium:service-check (Downe = service-level quality, Nielsen = interface-level quality).
What it loads into context
Frontmatter
129 tokensAlways available to the agent
SKILL.md
1,525 tokensWhen the skill is activated
Reference documents
3,303 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- The 10 Heuristics
- Complementary: interaction & visual axioms (optional, nudge-only)
- Output Format
- Theory Citations
Files
../../harness/design-principles.mddoc14,098 bytesSKILL.mdcore6,636 bytes
Read SKILL.md
# Usability Heuristic Evaluation
Evaluate interface-level usability using Jakob Nielsen's 10 heuristics (1994; titles unchanged, definitions refined 2020). This complements Downe's 15 Good Services principles: Downe checks end-to-end SERVICE quality, Nielsen checks screen-level INTERFACE quality. Both are needed for user-facing work.
## When to Use
- During L4 Delivery for any user-facing work (REVIEW via G-V10)
- After UI implementation, before marking delivery complete
- When users report confusion or friction
## The 10 Heuristics
### 1. Visibility of System Status
The system should always keep users informed about what is going on through timely and appropriate feedback.
- [ ] Loading states visible for any operation > 1 seconduser-interview
When your agent uses it
Guide for conducting Torres-style story-based interviews with the people whose experience you're researching, with bias mitigation and a JTBD lens.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
3,180 tokensWhen the skill is activated
Reference documents
6,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Pre-Interview (Mandatory)
- Question Design Rules
- During Interview
- Post-Interview Snapshot
- Async drip mode (added v0.219.0; a second mode, not a degraded live interview)
- Output
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytesSKILL.mdcore13,432 bytesSKILL.mdcore13,432 bytes
Read SKILL.md
# User Interview Guide
Discover opportunities through customer stories. Source: Torres (CDH), Kahneman, Christensen (JTBD).
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
user-needs-map
When your agent uses it
Map the needs of the people you're building or exploring for, independently of solutions, using Allen's User Needs Mapping methodology. Identifies underserved needs that feed into the Opportunity Solution Tree.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,642 tokensWhen the skill is activated
Reference documents
6,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- When to Use
- Workflow
- Canvas Output
- Bias Warning
- Theory Citations
- Handling User-Supplied Content
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytesSKILL.mdcore11,230 bytesSKILL.mdcore11,230 bytesSKILL.mdcore11,230 bytes
Read SKILL.md
# User Needs Mapping
Map what users need independently of any particular solution. Discover needs through research, not assumption. Source: Rich Allen (User Needs Mapping), connected to Wardley Mapping and Team Topologies.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
wardley-map
When your agent uses it
Create or update a Wardley Map of how any domain delivers value. Maps the needs it serves, the capabilities involved, how each is evolving (genesis to commodity), and strategic plays. Applies to any domain, not only software.
What it loads into context
Frontmatter
138 tokensAlways available to the agent
SKILL.md
3,930 tokensWhen the skill is activated
Reference documents
6,857 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file(s) before any Write/Edit
- Mapping Process
- Output
- Decision Log (MANDATORY per G-P4)
- Connection to Other Frameworks
- Postflight: Verify-After-Write (claim matches state)
Scripts executed separately
../../scripts/review_schedule.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py../../scripts/scale_locks.py
Files
../../engine/agent-operating-contract.mddoc24,482 bytes../../engine/reading-for-meaning.mddoc4,338 bytes../../scripts/review_schedule.pyruns12,839 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytes../../scripts/scale_locks.pyruns155,596 bytesSKILL.mdcore16,388 bytesSKILL.mdcore16,388 bytes
Read SKILL.md
# Wardley Mapping
Visualize your value chain and make strategic decisions. Source: Simon Wardley.
## Preflight: Read target canvas file(s) before any Write/Edit
**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.
**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.
**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:
wiring-contract
When your agent uses it
Derive this project's own integration conventions from what the code already does, draft them as a wiring contract, and hold new work to it. Closes the built-but-not-wired gap at L3 (walking skeleton) — a mechanism that ships and is never called reads green in every other check.
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
1,321 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Output
- Theory Citations
- Deliberately NOT a catalogue
Scripts executed separately
../../scripts/check_wiring_contract.py
Files
../../scripts/check_wiring_contract.pyruns17,804 bytesSKILL.mdcore5,789 bytesSKILL.mdcore5,789 bytesSKILL.mdcore5,789 bytes
Read SKILL.md
# Wiring Contract
Answer one question for this project and then keep answering it automatically: **when something is built here, what does it have to be connected to before it counts as done?**
The failure is not carelessness, it is structural. A model's context makes it unable to see whether the element it just generated is referenced anywhere else, so plausible-but-unreferenced code is the *expected* output. Across 304,362 verified AI-authored commits in 6,275 repositories, "unused variables or parameters" is the second most frequent issue class, and "undefined variable or reference" — writer and reader disagreeing about a name or path — is the most common runtime bug category. It does not wash out: AI-authored code survives **longer** than human-written code (53.9% vs 69.3% line death rate), so an orphan is *less* likely to be cleaned up than a human's.
Every ordinary signal misses it. Tests pass, coverage rises, lint is clean, review approves — because each of those verifies a thing **against itself**, and wiring is a property of a **pair**.
## When to Use
- **At L3, before implementation** — the walking-skeleton obligation (G-V13). A design is not complete until its joins are named.
- On an existing project, once, to discover what conventions it already has.
- After a structural change (new directory, new layer, a move) — **regenerate**, never hand-edit.
- When `check_wiring_contract.py` reports UNGOVERNED files you did not expect.xai-check
When your agent uses it
Explainability (XAI) audit for products containing AI components. Five-stage tier-scaled check: risk classification, stakeholder×question matrix, fidelity audit, system card, recourse path. Honest about what was validated functionally vs what needs user testing.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
3,420 tokensWhen the skill is activated
Reference documents
7,626 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Precondition: AI components detected
- Workflow (5 stages)
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Output
- Display to user
- Composition with other gates / skills
- What this skill does NOT do
- Theory citations
Files
../../jit-tooling/detector.mddoc26,354 bytesSKILL.mdcore13,880 bytesSKILL.mdcore13,880 bytes../../templates/ai-system-card.mddoc4,838 bytes
Read SKILL.md
# XAI Check Skill
Operational gate for the Explainability Theory Gate (Gate 13). Audits whether a product's AI components meet a defensible XAI bar — disclosure, decision-explanation, recourse, fidelity, system card — scaled to the AI Act risk tier.
This skill is **functionally-grounded** in Doshi-Velez & Kim's (2017) sense: it operates on artifacts and configuration, not on real users with real tasks. Output explicitly distinguishes `validated_functionally` from `needs_user_testing`. The honest tag is what passes Gate 13; user-grounded validation is recommended but not blocking.
**The gate reads this skill's record (v0.331.0).** On a product with AI components detected, an Explainability pass counts only when a `services[].xai` block holds a verdict for each stage the scale asks: at an L3 the tier (Stage 1); at an L4 or L5 every stage, with `recourse.verdict` asked from the `limited` tier up. A stage that does not apply takes a verdict saying so (`not_applicable`). The scale-lock gate and the release gate name the stage that is missing. Until 0.331.0 the gate passed on the status word.
## When to Use
- An L3's `release` or `close`, **only when `active-stack.yml :: ai_components.detected: true`**
- An L4's `release` — required when AI components reach user-affecting decisions (deny, recommend, rank, generate user-shown content)
- An L5's `release` — required for any user-facing AI feature at launch
- After any change to AI components, prompts, or surfaces that affect user-facing decisionsinterview
When your agent uses it
Compliant fixture: acknowledges wrapping convention.
What it loads into context
Frontmatter
15 tokensAlways available to the agent
SKILL.md
53 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore263 bytes
Read SKILL.md
# Interview
Per `security-trust.md#prompt-injection-defense-for-user-supplied-content`, user input is wrapped as untrusted_user_content before passing to model context.new_user_intake
When your agent uses it
Heuristic-candidate fixture: outside curated list but strong user-content signal.
What it loads into context
Frontmatter
25 tokensAlways available to the agent
SKILL.md
56 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore259 bytes
Read SKILL.md
# New User Intake
Ask the user for their input and record answers verbatim. This is user-supplied content the agent will process.interview
When your agent uses it
Non-compliant fixture: handles user content but no wrapping acknowledgment.
What it loads into context
Frontmatter
20 tokensAlways available to the agent
SKILL.md
38 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore208 bytes
Read SKILL.md
# Interview
This skill conducts an interview but does not mention the wrapping convention.badskill
When your agent uses it
Test fixture skill that writes to canvas without a Preflight block. Check 31 must surface this.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
74 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore322 bytes
Read SKILL.md
# Bad Skill
This skill writes to `.claude/canvas/purpose.yml` (Update canvas/purpose.yml) but lacks the required Preflight: Read target canvas file block. Check 31 should flag this skill.goodskill
When your agent uses it
Test fixture skill that writes to canvas AND carries the Preflight block. Check 31 must pass.
What it loads into context
Frontmatter
27 tokensAlways available to the agent
SKILL.md
124 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read target canvas file
Files
SKILL.mdcore520 bytes
Read SKILL.md
# Good Skill
This skill writes to `.claude/canvas/purpose.yml` (Update canvas/purpose.yml).
## Preflight: Read target canvas file
Before any canvas write, this skill reads the target file first per the Read-before-Write hard rule (anti-pattern #7 instance #5 prevention).
```
Read .claude/canvas/purpose.yml (limit: 1 for Edit, full Read for Write)
```
Then proceeds with the write.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
42 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
Files
SKILL.mdcore188 bytes
Read SKILL.md
# Fixture: diamond-assess SKILL.md WITHOUT Read-before-Recommend Preflight block (Check 41 fail case)
## Workflow
Body irrelevant for fixture; Check 41 should flag the missing preamble.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
78 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Preflight: Read-before-Recommend (gate-narration discipline)
- Workflow
Files
SKILL.mdcore368 bytes
Read SKILL.md
# Fixture: diamond-assess SKILL.md WITH Read-before-Recommend Preflight block (Check 41 pass case)
## Preflight: Read-before-Recommend (gate-narration discipline)
Hard rule placeholder for fixture coverage. Real skill carries the canonical Communication-Rule-citing block.
## Workflow
Body irrelevant for fixture; Check 41 only greps for the section marker above.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
43 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Output
Files
SKILL.mdcore180 bytes
Read SKILL.md
# Fixture: dora-check SKILL.md WITHOUT Postflight Verify-After-Write block (Check 42 fail case)
## Output
Body irrelevant for fixture; Check 42 should flag the missing preamble.When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
87 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Postflight: Verify-After-Write (write-narration-verification discipline)
- Output
Files
SKILL.mdcore367 bytes
Read SKILL.md
# Fixture: dora-check SKILL.md WITH Postflight Verify-After-Write block (Check 42 pass case)
## Postflight: Verify-After-Write (write-narration-verification discipline)
Hard rule placeholder for fixture coverage. Real skill carries the canonical AP#7-Stage-2a-citing block.
## Output
Body irrelevant for fixture; Check 42 only greps for the section marker above.ost-render
When your agent uses it
Test fixture for Check 43 — invalid identifier_exposure value.
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
103 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Identifier exposure
Files
SKILL.mdcore454 bytes
Read SKILL.md
# OST Render (fixture)
This skill intentionally uses a non-canonical `identifier_exposure` value to exercise Check 43's invalid-value failure path.
## Identifier exposure
Body section is present but the frontmatter value is not YES/NONE/MIXED.ost-render
When your agent uses it
Test fixture for Check 43 — body section missing.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
106 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When NOT to use
Files
SKILL.mdcore480 bytes
Read SKILL.md
# OST Render (fixture)
This skill intentionally omits the `## Identifier exposure` body section to exercise Check 43's missing-body failure path. Frontmatter is valid but the body audit-trail is absent.
## When NOT to use
Cosmetic content only; no Identifier exposure section present.ost-render
When your agent uses it
Test fixture for Check 43 — frontmatter missing identifier_exposure field.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
89 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Identifier exposure
Files
SKILL.mdcore429 bytes
Read SKILL.md
# OST Render (fixture)
This skill intentionally omits `identifier_exposure` from its metadata frontmatter to exercise Check 43's missing-frontmatter failure path.
## Identifier exposure
Body section is present but frontmatter is missing.ost-render
When your agent uses it
Test fixture for Check 43 — valid NONE declaration.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
126 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Identifier exposure
Files
SKILL.mdcore568 bytes
Read SKILL.md
# OST Render (fixture, declared NONE)
This skill has valid frontmatter (NONE) AND a `## Identifier exposure` body section. Check 43 should PASS.
## Identifier exposure
**Declared**: NONE
Scope, rationale (no identifier fields touched), anon-label convention (n/a), worked example (zero-identifier render), and fixture-not-applicable note would live here in production.ost-render
When your agent uses it
Test fixture for Check 43 — valid YES declaration.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
107 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Identifier exposure
Files
SKILL.mdcore476 bytes
Read SKILL.md
# OST Render (fixture)
This skill has valid frontmatter (YES) AND a `## Identifier exposure` body section. Check 43 should PASS.
## Identifier exposure
**Declared**: YES
Scope, rationale, anon-label convention, worked examples, and fixture pointer would live here in production.bvssh-check
When your agent uses it
What it loads into context
Frontmatter
5 tokensAlways available to the agent
SKILL.md
31 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Output
Files
SKILL.mdcore101 bytes
Read SKILL.md
# BVSSH
## Output
**Lead with the verdict; make Red pop** (Von Restorff)ice-score
When your agent uses it
What it loads into context
Frontmatter
4 tokensAlways available to the agent
SKILL.md
23 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore83 bytes
Read SKILL.md
# ICE
### Output
**Lead with the recommendation** (Hick)bvssh-check
When your agent uses it
What it loads into context
Frontmatter
5 tokensAlways available to the agent
SKILL.md
19 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Output
Files
SKILL.mdcore63 bytes
ice-score
When your agent uses it
What it loads into context
Frontmatter
4 tokensAlways available to the agent
SKILL.md
18 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore62 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
10 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore47 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
10 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore47 bytes
When your agent uses it
Has description but no name field.
What it loads into context
Frontmatter
10 tokensAlways available to the agent
SKILL.md
16 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore71 bytes
good_skill
When your agent uses it
Valid frontmatter.
What it loads into context
Frontmatter
12 tokensAlways available to the agent
SKILL.md
18 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore73 bytes
Skills included
- a11y-check
- adopt
- assumption-test
- bias-check
- bvssh-check
- canvas-health
- canvas-sync
- canvas-update
- corrections-audit
- count
- cycle-render
- cynefin-classify
- define-done
- definition-of-done
- delivery-bootstrap
- devils-advocate
- diamond-assess
- diamond-progress
- diamond-render
- dora-check
- eval-runner
- fan-out
- feedback-review
- framework-health
- friction-log
- gist-plan
- handoff
- harms-check
- ice-score
- interview
- jtbd-map
- launch-tier
- log-evidence
- metrics-detect
- metrics-pull
- migrate-from-legacy
- mocked-persona-interview
- ost-builder
- ost-render
- ping
- preflight
- privacy-check
- prompt-optimizer
- purpose-properties
- receipt-render
- reflexion
- regulatory-review
- render
- retrospective
- scaffold-cost-check
- security-review
- service-check
- setup
- start
- team-shape
- theory-fidelity
- threat-model
- usability-check
- user-interview
- user-needs-map
- wardley-map
- wiring-contract
- xai-check
- interview
- new_user_intake
- interview
- badskill
- goodskill
- ost-render
- ost-render
- ost-render
- ost-render
- ost-render
- bvssh-check
- ice-score
- bvssh-check
- ice-score
- good_skill
Repository facts
- License
- MIT
- Created
- Apr 7, 2026
- Last pushed
- Oct 31, 2026
- Forks
- 6
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 659 notes
plugins/mycelium/hooks/README.md:45Analysis incomplete: physical or joined line exceeds character limitplugins/mycelium/hooks/README.md:46Analysis incomplete: physical or joined line exceeds character limitplugins/mycelium/hooks/README.md:47Analysis incomplete: physical or joined line exceeds character limitplugins/mycelium/hooks/README.md:64Analysis incomplete: physical or joined line exceeds character limitplugins/mycelium/hooks/README.md:244Analysis incomplete: physical or joined line exceeds character limitplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/mycelium/hooks/hooks.codex-plugin.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 6 dangerous shell commandsin 4 files: plugins/mycelium/hooks/preflight.sh:84 plugins/mycelium/hooks/gate.sh:232 plugins/mycelium/hooks/guard-state-gate.sh:23 and 1 more
- 297 network referencesin 73 files: plugins/mycelium/engine/render-conventions.md:238 plugins/mycelium/scripts/check_evidence_links.py:73 setup/SKILL.md:4 and 70 more
- No hidden or obfuscated text
- No instruction overrides
- 250 executable scriptsin 84 files: plugins/mycelium/scripts/scale_locks.py:1 plugins/mycelium/scripts/check_source_class_fidelity.py:1 plugins/mycelium/scripts/check_test_authenticity.py:1 and 81 more
- 89 references to secretsin 14 files: plugins/mycelium/scripts/scale_locks.py:381 plugins/mycelium/jit-tooling/metrics-detector.md:23 plugins/mycelium/harness/anti-patterns.md:129 and 11 more
- No requests to vote in Hot
Show all 642 signals by file
.claude-plugin/marketplace.json
plugins/mycelium/.claude-plugin/plugin.json
- Network accessline 1
{ "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", - Network accessline 2
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", - Network accessline 6
"author": { "name": "H\u00e5vard Bartnes", "url": "https://github.com/haabe" - Network accessline 7
"name": "H\u00e5vard Bartnes", "url": "https://github.com/haabe" }, - Network accessline 8
"url": "https://github.com/haabe" - Network accessline 9
}, "homepage": "https://github.com/haabe/mycelium", "repository": "https://github.com/haabe/mycelium", - Network accessline 10
"homepage": "https://github.com/haabe/mycelium", - Network accessline 11
"repository": "https://github.com/haabe/mycelium",
plugins/mycelium/engine/canvas-guidance.yml
- Network accessline 442
# # Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 442
# # Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 442
# # Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 442
# # Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 443
# Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM # fleets are now the norm; products that themselves make production - Network accessline 443
# Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM # fleets are now the norm; products that themselves make production - Network accessline 443
# Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM # fleets are now the norm; products that themselves make production - Network accessline 443
# Source: [S5] Datadog, "State of AI Engineering" (2026) — # https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM # fleets are now the norm; products that themselves make production - Network accessline 444
# https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 444
# https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 444
# https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM - Network accessline 444
# https://www.datadoghq.com/state-of-ai-engineering/. Runtime LLM
plugins/mycelium/engine/render-conventions.md
- Network accessline 238
> _Render: `<skill-name>` v`<framework-version>`. Source: `<canvas-file-path>`. Canvas state as-of: `<canvas-_meta.last_validated>`. Format: `<format>`._ > > _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaid - Network accessline 238
> _Render: `<skill-name>` v`<framework-version>`. Source: `<canvas-file-path>`. Canvas state as-of: `<canvas-_meta.last_validated>`. Format: `<format>`._ > > _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaid - Network accessline 238
> _Render: `<skill-name>` v`<framework-version>`. Source: `<canvas-file-path>`. Canvas state as-of: `<canvas-_meta.last_validated>`. Format: `<format>`._ > > _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaid - Network accessline 238
> _Render: `<skill-name>` v`<framework-version>`. Source: `<canvas-file-path>`. Canvas state as-of: `<canvas-_meta.last_validated>`. Format: `<format>`._ > > _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaid - Network accessline 238
> _Render: `<skill-name>` v`<framework-version>`. Source: `<canvas-file-path>`. Canvas state as-of: `<canvas-_meta.last_validated>`. Format: `<format>`._ > > _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaid - Network accessline 240
> _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaidchart.com (external dependency; no Mycelium affiliation)._ - Network accessline 240
> _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaidchart.com (external dependency; no Mycelium affiliation)._ - Network accessline 240
> _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaidchart.com (external dependency; no Mycelium affiliation)._ - Network accessline 240
> _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaidchart.com (external dependency; no Mycelium affiliation)._ - Network accessline 240
> _For interactive editing or shareable URL, paste Mermaid blocks at https://mermaidchart.com (external dependency; no Mycelium affiliation)._ - Network accessline 275
published: - kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location - Network accessline 275
published: - kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location - Network accessline 275
published: - kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location - Network accessline 275
published: - kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location - Network accessline 275
published: - kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location - Network accessline 276
- kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location source: "docs/renders/opportunity-tree.html" # durable copy, project-local path - Network accessline 276
- kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location source: "docs/renders/opportunity-tree.html" # durable copy, project-local path - Network accessline 276
- kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location source: "docs/renders/opportunity-tree.html" # durable copy, project-local path - Network accessline 276
- kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location source: "docs/renders/opportunity-tree.html" # durable copy, project-local path - Network accessline 276
- kind: page # what the address serves: page | artifact | doc | gist address: "https://..." # the persistent, updatable location source: "docs/renders/opportunity-tree.html" # durable copy, project-local path - Network accessline 277
address: "https://..." # the persistent, updatable location - Network accessline 277
address: "https://..." # the persistent, updatable location - Network accessline 277
address: "https://..." # the persistent, updatable location - Network accessline 277
address: "https://..." # the persistent, updatable location - Network accessline 277
address: "https://..." # the persistent, updatable location
plugins/mycelium/engine/wayfinding.md
- Network accessline 5
Source: NNGroup "You Are Here" navigation pattern (https://www.nngroup.com/articles/navigation-you-are-here/). - Network accessline 5
Source: NNGroup "You Are Here" navigation pattern (https://www.nngroup.com/articles/navigation-you-are-here/). - Network accessline 5
Source: NNGroup "You Are Here" navigation pattern (https://www.nngroup.com/articles/navigation-you-are-here/).
plugins/mycelium/harness/anti-patterns.md
plugins/mycelium/harness/theory-tensions.md
- Network accessline 206
- PMI: *Reconciling Differences* (agile vs traditional PM) - SEBoK: Decision Management — context-driven trade studies over decision trees - All framework citations are in [docs/theories.md](https://github.com/haabe/mycelium/blob/main/docs/ - Network accessline 208
- All framework citations are in [docs/theories.md](https://github.com/haabe/mycelium/blob/main/docs/theories.md) (30+ frameworks)
plugins/mycelium/hooks/README.md
plugins/mycelium/hooks/absence-claim-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/autonomous-evidence-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/bash-state-guard.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/brownfield-gate.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/canvas-schema-check.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/change-log.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/ci-signal.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/codex-postfailure-shim.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/contract-part.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/correction-attribution-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/diamond-state-audit.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/discovery-gate.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/discovery-trigger-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/exposure-change.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/exposure-gate.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/framework-guard.sh
plugins/mycelium/hooks/gate-override-check.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/gate.sh
plugins/mycelium/hooks/guard-state-gate.sh
plugins/mycelium/hooks/install-runtime-hooks.sh
plugins/mycelium/hooks/key-shape-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/lesson-triggers.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/next-action-check.sh
plugins/mycelium/hooks/next-item-repeat.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/post-write-nudge.sh
plugins/mycelium/hooks/preflight.sh
plugins/mycelium/hooks/read-before-research-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/read-log.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/reflexion-gate.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/scale-lock-gate.sh
- Executable scriptline 1
#!/bin/bash
plugins/mycelium/hooks/scope-gate.sh
plugins/mycelium/hooks/session-start.sh
plugins/mycelium/hooks/shell-safety-guard.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/mycelium/hooks/stop-check.sh
plugins/mycelium/jit-tooling/active-stack.example.yml
plugins/mycelium/jit-tooling/metrics-detector.md
- Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted] - Access to secretsline 51
[Credential-related source omitted]
plugins/mycelium/scripts/_state_dir.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/advisory_ledger.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Access to secretsline 461
[Credential-related source omitted] - Access to secretsline 461
[Credential-related source omitted]
plugins/mycelium/scripts/check_assessment_landed.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_canvas_version_drift.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_citations.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_climatic_predictions.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_contact_recorded_as_prose.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_correction_attribution.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_cynefin_freshness.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_derived_fields.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_doctrine_due.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_dod_shape.py
plugins/mycelium/scripts/check_evidence_landing.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
plugins/mycelium/scripts/check_evidence_links.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 73
# Backtick excluded and stripped: markdown code spans (`https://x/`) were producing - Network accessline 92
] SNAP_REL = pathlib.Path(".claude/evals/metrics/evidence-links") UA = "Mozilla/5.0 (compatible; mycelium-linkcheck/1; +https://github.com/haabe/mycelium)" - Network accessline 94
UA = "Mozilla/5.0 (compatible; mycelium-linkcheck/1; +https://github.com/haabe/mycelium)" - Network accessline 151
# ILLUSTRATION, never evidence, and probing it produces a 404 that looks exactly # like a rotted citation. The first run of this check reported # https://example.com/market-report as pending rot; it sits in a COMMENT in - Network accessline 152
# like a rotted citation. The first run of this check reported # https://example.com/market-report as pending rot; it sits in a COMMENT in # landscape.yml demonstrating the evidence_sources format. Skipping them by domain - Network accessline 153
# https://example.com/market-report as pending rot; it sits in a COMMENT in - Network accessline 197
def _request(url: str, headers: dict[str, str], method: str = "GET") -> urllib.request.Request: - Network accessline 199
return urllib.request.Request(url, headers=headers, method=method) # noqa: S310 - guarded - Network accessline 202
def _urlopen(req: urllib.request.Request, timeout: int): - Network accessline 204
return urllib.request.urlopen(req, timeout=timeout) # noqa: S310 - guarded - Network accessline 213
# A URL carrying an unexpanded variable is a TEMPLATE, not a citation. The widened # run surfaced `https://api.appstoreconnect.apple.com/v1/apps/$APPSTORE_APP_ID` - Network accessline 214
# run surfaced `https://api.appstoreconnect.apple.com/v1/apps/$APPSTORE_APP_ID` - Network accessline 293
# GITHUB ANSWERS ROBOTS WITH 404, NOT 403, AND THAT NEARLY COST US ELEVEN LINKS. # Verified 2026-08-17: `https://github.com/haabe/mycelium/commit/96b485e` returns 404 to - Network accessline 294
# Verified 2026-08-17: `https://github.com/haabe/mycelium/commit/96b485e` returns 404 to - Network accessline 295
# curl while `gh api repos/haabe/mycelium/commits/96b485e` returns the full SHA — the - Network accessline 312
owner, repo, rest = parts[0], parts[1], parts[2:] if not rest: api = f"https://api.github.com/repos/{owner}/{repo}" - Network accessline 313
if not rest: api = f"https://api.github.com/repos/{owner}/{repo}" elif rest[0] == "commit" and len(rest) > 1: - Network accessline 314
api = f"https://api.github.com/repos/{owner}/{repo}" - Network accessline 315
elif rest[0] == "commit" and len(rest) > 1: api = f"https://api.github.com/repos/{owner}/{repo}/commits/{rest[1]}" elif rest[0] == "issues" and len(rest) > 1 and rest[1].isdigit(): - Network accessline 316
api = f"https://api.github.com/repos/{owner}/{repo}/commits/{rest[1]}" - Network accessline 317
elif rest[0] == "issues" and len(rest) > 1 and rest[1].isdigit(): api = f"https://api.github.com/repos/{owner}/{repo}/issues/{rest[1]}" elif rest[0] in ("issues", "discussions", "pulls", "tree", "blob"): - Network accessline 318
api = f"https://api.github.com/repos/{owner}/{repo}/issues/{rest[1]}" - Network accessline 319
elif rest[0] in ("issues", "discussions", "pulls", "tree", "blob"): api = f"https://api.github.com/repos/{owner}/{repo}" # repo-level existence else: - Network accessline 320
api = f"https://api.github.com/repos/{owner}/{repo}" # repo-level existence
plugins/mycelium/scripts/check_field_wiring.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_hook_delivery.py
plugins/mycelium/scripts/check_ice_aggregate.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_idle_opportunities.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
plugins/mycelium/scripts/check_instrument_contract.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_key_shape.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_log_reconcile.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_merge_markers.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_named_people_unactioned.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_negative_control.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
plugins/mycelium/scripts/check_opportunity_shape.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_primary_theory_gated.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_published_records.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
plugins/mycelium/scripts/check_purpose_stance.py
plugins/mycelium/scripts/check_reply_owed.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_retirement_candidates.py
plugins/mycelium/scripts/check_scale_occupancy.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_source_authenticity.py
plugins/mycelium/scripts/check_source_class_fidelity.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
plugins/mycelium/scripts/check_source_independence.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_stale_prose.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_test_authenticity.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
plugins/mycelium/scripts/check_touch_log_order.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/check_upstream_candidates.py
plugins/mycelium/scripts/check_wiring.py
plugins/mycelium/scripts/check_wiring_contract.py
plugins/mycelium/scripts/codex_plugin_hooks.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/count_builder_row.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/derive_closing_path.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/install_git_secret_hook.py
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file; content unavailable - Network accessline 31
else echo "Mycelium: gitleaks is not installed, so this commit was not scanned for secrets." >&2 echo "Install it: https://github.com/gitleaks/gitleaks" >&2 - Network accessline 32
echo "Mycelium: gitleaks is not installed, so this commit was not scanned for secrets." >&2 echo "Install it: https://github.com/gitleaks/gitleaks" >&2 fi - Network accessline 33
echo "Install it: https://github.com/gitleaks/gitleaks" >&2 - Access to secretsline 56
[Credential-related source omitted]
plugins/mycelium/scripts/migrate_phase.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/mycelium/scripts/mutation_sample.py
plugins/mycelium/scripts/render_diamonds.py
- Executable scriptline 1
Executable file
plugins/mycelium/scripts/review_schedule.py
plugins/mycelium/scripts/scale_locks.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 381
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 1121
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2527
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2635
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted] - Access to secretsline 2720
[Credential-related source omitted]
plugins/mycelium/scripts/validate_mermaid.py
plugins/mycelium/skills/a11y-check/SKILL.md
- Network accessline 5
instruction_budget: "26" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/adopt/SKILL.md
- Network accessline 5
instruction_budget: "60" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/assumption-test/SKILL.md
- Network accessline 5
instruction_budget: "38" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/bias-check/SKILL.md
- Network accessline 5
instruction_budget: "27" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/bvssh-check/SKILL.md
- Network accessline 5
instruction_budget: "50" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/canvas-health/SKILL.md
- Network accessline 5
instruction_budget: "87" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/canvas-sync/SKILL.md
- Network accessline 5
instruction_budget: "8" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gate - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/canvas-update/SKILL.md
- Network accessline 5
instruction_budget: "12" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/corrections-audit/SKILL.md
- Network accessline 5
instruction_budget: "40" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/count/SKILL.md
- Network accessline 4
metadata: framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness - Network accessline 5
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 6
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/cynefin-classify/SKILL.md
- Network accessline 5
instruction_budget: "20" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/define-done/SKILL.md
- Network accessline 5
instruction_budget: "48" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 5
instruction_budget: "48" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/definition-of-done/SKILL.md
- Network accessline 5
instruction_budget: "65" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/delivery-bootstrap/SKILL.md
- Network accessline 5
instruction_budget: "54" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/devils-advocate/SKILL.md
- Network accessline 5
instruction_budget: "26" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/diamond-assess/SKILL.md
- Network accessline 5
instruction_budget: "82" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/diamond-progress/SKILL.md
- Network accessline 5
instruction_budget: "205" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory ga - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/dora-check/SKILL.md
- Network accessline 5
instruction_budget: "126" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory ga - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 154
**Sources**: - [S1] Faros AI, *Ten takeaways from the AI Engineering Report 2026: The Acceleration Whiplash*, 2026-04-12. https://www.faros.ai/blog/ai-acceleration-whiplash-takeaways - Network accessline 155
- [S1] Faros AI, *Ten takeaways from the AI Engineering Report 2026: The Acceleration Whiplash*, 2026-04-12. https://www.faros.ai/blog/ai-acceleration-whiplash-takeaways - Network accessline 156
- [S2] Faros AI, *Harness engineering: What makes AI coding agents work in 2026*, 2026-05-22. https://www.faros.ai/blog/harness-engineering - Network accessline 157
- [S5] Datadog, *State of AI Engineering* (production LLM telemetry, 1,000+ customers), 2026. https://www.datadoghq.com/state-of-ai-engineering/
plugins/mycelium/skills/eval-runner/SKILL.md
- Network accessline 5
instruction_budget: "41" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/fan-out/SKILL.md
- Network accessline 5
instruction_budget: "22" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/feedback-review/SKILL.md
- Network accessline 5
instruction_budget: "55" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/framework-health/SKILL.md
- Network accessline 5
instruction_budget: "50" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/friction-log/SKILL.md
- Network accessline 5
instruction_budget: "22" framework_dependency: "mycelium" framework_dependency_note: "Designed to run within the Mycelium framework (https://github.com/haabe/mycelium)." - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "Designed to run within the Mycelium framework (https://github.com/haabe/mycelium)." --- - Network accessline 7
framework_dependency_note: "Designed to run within the Mycelium framework (https://github.com/haabe/mycelium)."
plugins/mycelium/skills/gist-plan/SKILL.md
- Network accessline 5
instruction_budget: "32" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/handoff/SKILL.md
- Network accessline 5
instruction_budget: "47" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/harms-check/SKILL.md
- Network accessline 5
instruction_budget: "44" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/ice-score/SKILL.md
- Network accessline 5
instruction_budget: "35" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 176
> **Licence of this table.** It is adapted from "Confidence Meter" by Itamar Gilad, which he > licenses under Creative Commons Attribution-ShareAlike 4.0 International > (http://creativecommons.org/licenses/by-sa/4.0/; the statement is in h - Network accessline 177
> licenses under Creative Commons Attribution-ShareAlike 4.0 International > (http://creativecommons.org/licenses/by-sa/4.0/; the statement is in his spreadsheet). Changes > made here: his rows are laid out as one table with the group caps - Network accessline 178
> (http://creativecommons.org/licenses/by-sa/4.0/; the statement is in his spreadsheet). Changes
plugins/mycelium/skills/interview/SKILL.md
- Network accessline 5
instruction_budget: "110" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory ga - Network accessline 5
instruction_budget: "110" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory ga - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/jtbd-map/SKILL.md
- Network accessline 5
instruction_budget: "6" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gate - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/launch-tier/SKILL.md
- Network accessline 5
instruction_budget: "62" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/log-evidence/SKILL.md
- Network accessline 5
instruction_budget: "58" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/metrics-detect/SKILL.md
- Network accessline 5
instruction_budget: "19" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/metrics-pull/SKILL.md
- Network accessline 5
instruction_budget: "47" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/migrate-from-legacy/SKILL.md
- Network accessline 4
metadata: framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness - Network accessline 5
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 6
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/mocked-persona-interview/SKILL.md
- Network accessline 5
instruction_budget: "70" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/ost-builder/SKILL.md
- Network accessline 5
instruction_budget: "47" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/ost-render/SKILL.md
- Network accessline 118
Per `engine/render-conventions.md#hard-rule-consent--privacy-gate`. For every `evidence_sources` entry AND every named-individual mention in `notes` prose: - Skip URL-shaped entries (`http://`, `https://`). - Network accessline 119
- Skip URL-shaped entries (`http://`, `https://`).
plugins/mycelium/skills/ping/SKILL.md
- Network accessline 5
metadata: framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/preflight/SKILL.md
- Network accessline 5
instruction_budget: "45" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/privacy-check/SKILL.md
- Network accessline 5
instruction_budget: "37" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/prompt-optimizer/SKILL.md
- Network accessline 5
instruction_budget: "17" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/purpose-properties/SKILL.md
- Network accessline 5
instruction_budget: "21" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 22
Full contract: https://github.com/haabe/mycelium/blob/main/docs/purpose-stance.md (it lives in the repository, not in the installed plugin).
plugins/mycelium/skills/receipt-render/SKILL.md
- Network accessline 137
1. **Origin line** (for whoever receives it): > _Produced with Mycelium, a product-thinking discipline for AI agents. What it is + how this receipt was generated: https://github.com/haabe/mycelium/blob/main/docs/receipts/handoff.md_ - Network accessline 138
> _Produced with Mycelium, a product-thinking discipline for AI agents. What it is + how this receipt was generated: https://github.com/haabe/mycelium/blob/main/docs/receipts/handoff.md_ - Network accessline 140
2. **Adopter share-back line** (Flow A — only in `markdown`): > _Built something with this? If you want, post it here → https://github.com/haabe/mycelium/discussions/new?category=show-and-tell&title=Built%20something%20with%20Mycelium&bo - Network accessline 141
> _Built something with this? If you want, post it here → https://github.com/haabe/mycelium/discussions/new?category=show-and-tell&title=Built%20something%20with%20Mycelium&body=<url-encoded: what were you building, and what did the receipt
plugins/mycelium/skills/reflexion/SKILL.md
- Network accessline 5
instruction_budget: "52" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/regulatory-review/SKILL.md
- Network accessline 5
instruction_budget: "42" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/retrospective/SKILL.md
- Network accessline 5
instruction_budget: "58" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/scaffold-cost-check/SKILL.md
- Network accessline 5
instruction_budget: "42" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/security-review/SKILL.md
- Network accessline 5
instruction_budget: "42" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/service-check/SKILL.md
- Network accessline 5
instruction_budget: "52" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/setup/SKILL.md
- Network accessline 4
metadata: framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness - Network accessline 4
metadata: framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness - Network accessline 5
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 5
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 6
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 6
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i - Network accessline 231
This project uses [Mycelium](https://github.com/haabe/mycelium) for product-thinking discipline. - Network accessline 231
This project uses [Mycelium](https://github.com/haabe/mycelium) for product-thinking discipline. - Network accessline 260
This project also uses the [Mycelium plugin](https://github.com/haabe/mycelium). Project-specific state lives in `.claude/canvas/`, `.claude/diamonds/`, `.claude/memory/`. The framework auto-fires via Claude Code plugin hooks; cross-agent u - Network accessline 260
This project also uses the [Mycelium plugin](https://github.com/haabe/mycelium). Project-specific state lives in `.claude/canvas/`, `.claude/diamonds/`, `.claude/memory/`. The framework auto-fires via Claude Code plugin hooks; cross-agent u - Network accessline 409
- **Not a git repository**: skip the offer. - **If gitleaks is not installed** (`command -v gitleaks` finds nothing): say so in the same message, with where to get it (https://github.com/gitleaks/gitleaks). Until then Mycelium's - Network accessline 409
- **Not a git repository**: skip the offer. - **If gitleaks is not installed** (`command -v gitleaks` finds nothing): say so in the same message, with where to get it (https://github.com/gitleaks/gitleaks). Until then Mycelium's - Network accessline 410
- **If gitleaks is not installed** (`command -v gitleaks` finds nothing): say so in the same message, with where to get it (https://github.com/gitleaks/gitleaks). Until then Mycelium's own check at the agent's commit and push falls back - Network accessline 410
- **If gitleaks is not installed** (`command -v gitleaks` finds nothing): say so in the same message, with where to get it (https://github.com/gitleaks/gitleaks). Until then Mycelium's own check at the agent's commit and push falls back - Network accessline 411
message, with where to get it (https://github.com/gitleaks/gitleaks). Until then Mycelium's - Network accessline 411
message, with where to get it (https://github.com/gitleaks/gitleaks). Until then Mycelium's - Network accessline 451
Receipts case: [docs/receipts/cases/2026-05-08-bentes-install-model.md](https://github.com/haabe/mycelium/blob/main/docs/receipts/cases/2026-05-08-bentes-install-model.md). Daniel Bentes (BDSK author, Produktleder.no) surfaced the install-m - Network accessline 451
Receipts case: [docs/receipts/cases/2026-05-08-bentes-install-model.md](https://github.com/haabe/mycelium/blob/main/docs/receipts/cases/2026-05-08-bentes-install-model.md). Daniel Bentes (BDSK author, Produktleder.no) surfaced the install-m
plugins/mycelium/skills/start/SKILL.md
- Network accessline 4
metadata: framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness - Network accessline 5
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 6
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/team-shape/SKILL.md
- Network accessline 5
instruction_budget: "26" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/theory-fidelity/SKILL.md
- Network accessline 5
instruction_budget: "55" framework_dependency: "mycelium" framework_dependency_note: "Designed to run within Mycelium (https://github.com/haabe/mycelium), where docs/theories.md provides the claimed-theory inventory. On a non-Mycelium p - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "Designed to run within Mycelium (https://github.com/haabe/mycelium), where docs/theories.md provides the claimed-theory inventory. On a non-Mycelium project it audits whatever t - Network accessline 7
framework_dependency_note: "Designed to run within Mycelium (https://github.com/haabe/mycelium), where docs/theories.md provides the claimed-theory inventory. On a non-Mycelium project it audits whatever theory/methodology doc the project m
plugins/mycelium/skills/threat-model/SKILL.md
- Network accessline 5
instruction_budget: "28" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/usability-check/SKILL.md
- Network accessline 5
instruction_budget: "45" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/user-interview/SKILL.md
- Network accessline 5
instruction_budget: "39" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/user-needs-map/SKILL.md
- Network accessline 5
instruction_budget: "35" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/wardley-map/SKILL.md
- Network accessline 5
instruction_budget: "10" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/wiring-contract/SKILL.md
- Network accessline 5
instruction_budget: "38" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
plugins/mycelium/skills/xai-check/SKILL.md
- Network accessline 5
instruction_budget: "60" framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gat - Network accessline 6
framework_dependency: "mycelium" framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior th - Network accessline 7
framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin i
tests/bash/fixtures/check_55/bad/plugins/mycelium/hooks/hooks.json
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 500 facts
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:238Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:238Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:238Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:238Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:238Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:240Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:240Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:240Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:240Low confidence
- Network access in prose of documentationplugins/mycelium/engine/render-conventions.md:240Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:275Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:275Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:275Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:275Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:275Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:276Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:276Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:276Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:276Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:276Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:277Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:277Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:277Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:277Low confidence
- Network access in code of documentationplugins/mycelium/engine/render-conventions.md:277Low confidence
- Network access in prose of documentationplugins/mycelium/engine/wayfinding.md:5Low confidence
- Network access in prose of documentationplugins/mycelium/engine/wayfinding.md:5Low confidence
- Network access in prose of documentationplugins/mycelium/engine/wayfinding.md:5Low confidence
- Access to secrets in prose of documentationplugins/mycelium/harness/anti-patterns.md:129Low confidence
- Access to secrets in prose of documentationplugins/mycelium/harness/anti-patterns.md:129Low confidence
- Access to secrets in prose of documentationplugins/mycelium/harness/anti-patterns.md:129Low confidence
- Network access in prose of documentationplugins/mycelium/harness/theory-tensions.md:206Low confidence
- Network access in prose of documentationplugins/mycelium/harness/theory-tensions.md:208Low confidence
- Network access in prose of documentationplugins/mycelium/hooks/README.md:175Low confidence
- Network access in prose of documentationplugins/mycelium/hooks/README.md:349Low confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/absence-claim-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/autonomous-evidence-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/bash-state-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/brownfield-gate.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/canvas-schema-check.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/change-log.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/ci-signal.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/codex-postfailure-shim.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/contract-part.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/correction-attribution-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/diamond-state-audit.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/discovery-gate.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/discovery-trigger-guard.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/exposure-change.sh:1High confidence
- Executable script in code of a file that runsplugins/mycelium/hooks/exposure-gate.sh:1High confidence
and 450 more
Only the first 500 facts are listed.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/mycelium/skills/a11y-check/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/mycelium/skills/a11y-check/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/mycelium/skills/a11y-check/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/mycelium/skills/a11y-check/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
