Not in the top 1,000 by GitHub stars
sno-ai/sno-station-skills
Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.
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/sno-station-standalone/skills/agentic-walkthrough/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/charter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/e2e-environment-preflight/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/e2e-red-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/first-principles-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/less-is-more/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/owner-intent-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/python-coder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/rust-coder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/shellscript-coder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/test-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
plugins/sno-station-standalone/skills/ts-coder/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/H-reporting-and-visibility/away-brief/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/H-reporting-and-visibility/catch-report/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/agentic-walkthrough/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/first-principles-review/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/less-is-more/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/owner-intent-audit/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/peer-review/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/J-peer-review-and-audit/test-writer/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/codex-coder/overlay/claude/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/codex-coder/overlay/codex/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/medic/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/python-coder/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/rust-coder/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/shellscript-coder/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/sno-cli/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/M-build-and-rollout/ts-coder/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/R-recursive-self-improvement/rem-reflect/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/S-communication-and-handoff/handoff/skill/SKILL.md
Week of Nov 2, 2026 · +44 / −8 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
- 42 Nothing can be verified with A and there is no A to release, so the procedure below does not apply;
- 43 follow "When the sender is gone" instead. It only works if A kept a progress record.
+ 42 The recovery initiator uses the recorded owner authorization to drive the same receiver
+ 43 release path; it never fabricates a response from A. Follow "When the sender is gone".
+ 62 Keep Next accurate before undertaking it, including its expected observable result.
+ 63 Save the most recent failed operation, target and error, the continuing report destination,
+ 64 and the exact vendor session identity when available. Update Done and Next at real task
+ 65 boundaries, before an orderly interruption and before Claude compaction.
+ 80 Normal call stores the complete launcher as `X-Type: call` mail and submits one short
+ 81 `REACH-RING` cue, not its full text, to the terminal. B reads the addressed inbox and
+ 82 exact mail file, then outputs its transport delivery receipt before following the launcher.
+ 83 Call mail is transport-only: never accept or complete it. Dismiss handled call mail;
+ 84 keep the original task card and its Reply-To for acceptance and completion.
+ 85 Mail storage or a cue alone never proves readiness, release or task completion.
+ 120 Release and pause instructions use the same mailbox call plus one short cue. Their
+ 121 transport mail creates no new owned work; it never replaces B's actual work card.
- 147 assumptions, Risks and open questions. The command never touches text outside the markers.
- 148
- 149 Run it after every finished task and then update Done and Next. An agent that does this can be
+ 159 assumptions, Risks and open questions, plus Known failure, Report destination and Reach card.
+ 160 The command never touches text outside the markers. Record settled decisions and exclusions,
+ 161 the exact unfinished action and expected result, the latest failed operation/target/error,
+ 162 the continuing report destination and any real card identity/recipient in these sections.
+ 163
+ 164 With no file argument and a known native session identity, the command uses
+ 165 `<Sno profile>/station/handoff/<session-id>.md`; the Sno profile defaults to `~/.sno`.
+ 166 SessionStart and next-prompt continuity injection read that same file. A new receiver keeps
+ 167 the complete readable brief and maintains it under its own session's default path too.
+ 168 The machine block preserves available runtime/session identity; absent optional metadata
+ 169 does not make a readable task unusable. Never choose a different "last session".
+ 170
+ 171 Keep Next accurate before taking it; run the command at real task boundaries and before
+ 172 an orderly stop or compaction, then update Done and Next. An agent that does this can be
- 161 The receiver B works from the progress record alone. Steps 3 to 7 above do not apply: there is no A to
- 162 verify with, release, or unregister.
+ 184 Try the exact original vendor session first through `sno rotate-agent-resume`. An unavailable
+ 185 session rebuilds from the same readable record, applicable Reach card and scoped memory.
+ 186 Known exhausted quota skips original-vendor execution; unknown quota or authentication failure
+ 187 is not exhausted quota. If no other vendor can run, retain the brief and report the quota
+ 188 blocker and that other-vendor takeover was skipped; no recovery has completed yet.
+ 189
+ 190 For a new conversation, the recovery initiator carries the actual owner authorization,
+ 191 uses its own identity for any receiver card and drives the same readiness/release path.
+ 192 Keep the original X-Work and card relationship and continuing Reply-To; never fabricate A's
+ 193 cancellation or release. Correlate B's actual card recipient with its new
+ 194 `HANDOFF_RELEASED <nonce>` output. The absent sender makes no further task writes.
- 174 started B, and say that the receiver started without a release from the sender.
+ 206 started B. State one outcome: `resumed` for the exact original conversation, `rebuilt` for a
+ 207 new conversation with recovered task state, or `lost` for essential task facts that could
+ 208 not be recovered. Separately report whether the unfinished action completed, remains
+ 209 unfinished or is blocked, and identify any missing facts or original-conversation loss.
+ 210 A process start, acknowledgement or release is not task completion.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/S-communication-and-handoff/heartbeat/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/S-communication-and-handoff/join-talk/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/S-communication-and-handoff/reach/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/S-communication-and-handoff/rotate-agent/skill/SKILL.md
Week of Nov 2, 2026 · +35 / −11 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
- 49 After every completed task run `sno handoff-checkpoint <record>` outside the checkout, then update Done and Next. Commit only if the owner authorized it.
+ 49 Keep the exact unfinished action and expected result in Next before undertaking it. At real task boundaries, before an orderly stop and before compaction run `sno handoff-checkpoint` (or the same explicit record path) and update Done, Next and the latest failed operation/target/error. Commit only if the owner authorized it.
- 173 Use a distinct work label per candidate attempt. The record must belong to the same
- 174 checkout. `MATCH` means unchanged; `DRIFT` is passed to B to inspect before continuing.
- 175 B reads the whole record and emits fresh `RESUME_ACK` without editing. The script
- 176 checks its answer provider before releasing B to continue; failed acknowledgement
- 177 leaves B paused and logs the failure, so the caller can try the next candidate.
- 178 A missing release receipt needs inspection: B may already own the work.
- 179 The last line on success is `RESUMED seat=<address> verify=MATCH|DRIFT`.
- 180
- 181 B prints `DONE_<work>` when finished, or `BLOCKED_<work> <reason>` when the owner is
- 182 needed. It never prints `DONE_<work>` while any task waits on the owner.
+ 173 The record must belong to the same checkout. The command first uses its exact recorded
+ 174 vendor session identity with `claude -p --resume <id>` or `codex exec resume <id> <prompt>`;
+ 175 it never chooses an unrelated latest session. Missing identity skips only native resume.
+ 176 If native resume is unavailable, it rebuilds from the same readable brief, applicable
+ 177 Reach card and existing scoped memory retrieval in the original vendor when usable.
+ 178 Known exhausted quota skips both original-vendor entries and uses the selected other
+ 179 vendor. Unknown quota or authentication failure is not called exhausted quota. If no
+ 180 other vendor can execute, it retains the brief and says takeover was skipped and no
+ 181 recovery completed; a quota blocker does not mean task facts were lost.
+ 182
+ 183 `MATCH`/`DRIFT` are auxiliary checkout observations for reconciliation, not admission
+ 184 requirements. B reads the whole record and emits fresh `HANDOFF_READY <nonce>` without
+ 185 editing. The command checks the existing selected-provider information where applicable,
+ 186 then sends `HANDOFF_RELEASE <nonce>` and requires `HANDOFF_RELEASED <nonce>` from new
+ 187 receiver output before B writes. All calls use stored full-text call mail plus one short
+ 188 cue; no repeated Enter or second handshake. Call mail is transport-only and never an
+ 189 owned work card. Card-backed work preserves the original chain, actual receiver card
+ 190 recipient and Reply-To; direct owner work does not invent an original card. The recovery
+ 191 initiator uses its real authorization and never fabricates a response from an absent A.
+ 192 An uncertain release needs inspection of that receiver and Reach records: B may own the
+ 193 work, so never start another receiver. Reach's existing seat/receipt records suffice;
+ 194 there is no second per-work once file.
+ 195
+ 196 Output distinguishes `resumed` (the exact original conversation), `rebuilt` (new
+ 197 conversation; original conversation lost) and `lost` (essential next-step facts
+ 198 unrecoverable). Each is separate from `next_action=completed|unfinished|blocked`.
+ 199 Startup, readiness and release report the action unfinished; they never prove it
+ 200 completed. Completion requires the receiver's actual next-step result. B maintains the
+ 201 complete brief at its default `<Sno profile>/station/handoff/<session-id>.md` path for
+ 202 next-prompt and post-compaction injection, retaining the prior complete record.
+ 203
+ 204 B reports the actual next action result and earlier failure to the continuing destination
+ 205 in the brief (or `--report-to`). A missing optional observation or failed report delivery
+ 206 does not revoke B's ownership or let A resume competing task writes.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/S-communication-and-handoff/subscription-quota-check/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/charter/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/cos/skills/cos/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/cos/skills/cos-evolve/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/cos/skills/cos-review/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/cos/skills/cos-watch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/deliver/skill/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/pl/skills/pl/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/pl/skills/pl-analyze/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/pl/skills/pl-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/pl/skills/pl-dispatch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/pl/skills/pl-env/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
skills/T-delegation-and-work-orders/pl/skills/pl-watch/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
fec338848902 → 1ca8a66158bc
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → fec338848902
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 1ca8a66158bc9ca26c288c6d5e7ebcf2ffb8491a
git clone --filter=blob:none --no-checkout https://github.com/sno-ai/sno-station-skills.git .hotskills/sno-ai-sno-station-skills && git -C .hotskills/sno-ai-sno-station-skills checkout --detach 1ca8a66158bc9ca26c288c6d5e7ebcf2ffb8491a
# Copy each selected skill directory from .hotskills/sno-ai-sno-station-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/sno-ai/sno-station-skills.git .hotskills/sno-ai-sno-station-skills && git -C .hotskills/sno-ai-sno-station-skills checkout --detach 1ca8a66158bc9ca26c288c6d5e7ebcf2ffb8491a
# Copy each selected skill directory from .hotskills/sno-ai-sno-station-skills into .agents/skills/<skill-name>/861GitHub stars
3stars in 7 days
50skills in this repository
31commits in 30 days
Heat
4.2- 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
Individual skills in this repository
- agentic-walkthrough
plugins/sno-station-standalone/skills/agentic-walkthrough - charter
plugins/sno-station-standalone/skills/charter - e2e-environment-preflight
plugins/sno-station-standalone/skills/e2e-environment-preflight - e2e-red-triage
plugins/sno-station-standalone/skills/e2e-red-triage - first-principles-review
plugins/sno-station-standalone/skills/first-principles-review - less-is-more
plugins/sno-station-standalone/skills/less-is-more - owner-intent-audit
plugins/sno-station-standalone/skills/owner-intent-audit - python-coder
plugins/sno-station-standalone/skills/python-coder - rust-coder
plugins/sno-station-standalone/skills/rust-coder - shellscript-coder
plugins/sno-station-standalone/skills/shellscript-coder - test-writer
plugins/sno-station-standalone/skills/test-writer - ts-coder
plugins/sno-station-standalone/skills/ts-coder - agentic-time-estimate
skills/H-reporting-and-visibility/agentic-time-estimate/skill - away-brief
skills/H-reporting-and-visibility/away-brief/skill - catch-report
skills/H-reporting-and-visibility/catch-report/skill - agentic-walkthrough
skills/J-peer-review-and-audit/agentic-walkthrough/skill - e2e-environment-preflight
skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight - e2e-red-triage
skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage - first-principles-review
skills/J-peer-review-and-audit/first-principles-review/skill - less-is-more
skills/J-peer-review-and-audit/less-is-more/skill - owner-intent-audit
skills/J-peer-review-and-audit/owner-intent-audit/skill - peer-review
skills/J-peer-review-and-audit/peer-review/skill - test-writer
skills/J-peer-review-and-audit/test-writer/skill - codex-coder
skills/M-build-and-rollout/codex-coder/overlay/claude - codex-coder
skills/M-build-and-rollout/codex-coder/overlay/codex - medic
skills/M-build-and-rollout/medic/skill - python-coder
skills/M-build-and-rollout/python-coder/skill - rust-coder
skills/M-build-and-rollout/rust-coder/skill - shellscript-coder
skills/M-build-and-rollout/shellscript-coder/skill - sno-cli
skills/M-build-and-rollout/sno-cli/skill - ts-coder
skills/M-build-and-rollout/ts-coder/skill - rem-reflect
skills/R-recursive-self-improvement/rem-reflect/skill - handoff
skills/S-communication-and-handoff/handoff/skill - heartbeat
skills/S-communication-and-handoff/heartbeat/skill - join-talk
skills/S-communication-and-handoff/join-talk/skill - reach
skills/S-communication-and-handoff/reach/skill - rotate-agent
skills/S-communication-and-handoff/rotate-agent/skill - subscription-quota-check
skills/S-communication-and-handoff/subscription-quota-check/skill - charter
skills/T-delegation-and-work-orders/charter/skill - cos
skills/T-delegation-and-work-orders/cos/skills/cos - cos-evolve
skills/T-delegation-and-work-orders/cos/skills/cos-evolve - cos-review
skills/T-delegation-and-work-orders/cos/skills/cos-review - cos-watch
skills/T-delegation-and-work-orders/cos/skills/cos-watch - deliver
skills/T-delegation-and-work-orders/deliver/skill - pl
skills/T-delegation-and-work-orders/pl/skills/pl - pl-analyze
skills/T-delegation-and-work-orders/pl/skills/pl-analyze - pl-audit
skills/T-delegation-and-work-orders/pl/skills/pl-audit - pl-dispatch
skills/T-delegation-and-work-orders/pl/skills/pl-dispatch - pl-env
skills/T-delegation-and-work-orders/pl/skills/pl-env - pl-watch
skills/T-delegation-and-work-orders/pl/skills/pl-watch
How it works
agentic-walkthrough
When your agent uses it
Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect, capture one observable per hop, and report a result a no-op could not produce.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,537 tokensWhen the skill is activated
Reference documents
174,692 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Walk the path — be the program, read, don't run
- 2. Probe every hop that has to be real
- 3. Report a number, not an impression
- Before any absence becomes a finding, check your instrument
Scripts executed separately
scripts/selftest/run-selftest.sh../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/calibration.t../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/run-selftest.sh../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/time-left../../../../skills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief../../../../skills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t../../../../skills/H-reporting-and-visibility/away-brief/skill/scripts/selftest/run-selftest.sh../../../../skills/H-reporting-and-visibility/catch-report/skill/scripts/catch-report../../../../skills/H-reporting-and-visibility/catch-report/skill/scripts/catch-report.t../../../../skills/H-reporting-and-visibility/catch-report/skill/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/agentic-walkthrough/skill/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/extract-prd-handoff.py../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-extractor-test.sh../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-scenarios.sh../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/verify-manual-only.sh../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/verify-workflow-policy.sh../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/validate-report.py../../../../skills/J-peer-review-and-audit/less-is-more/skill/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/owner-intent-audit/skill/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/owner-intent-audit/skill/scripts/selftest/verify-review-boundary.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/lib/sno-model.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/review-backfill.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/review-findings.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/review-receipt.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/run-adversarial-review.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/cursor-process-group.t../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-cross-vendor.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-model-settings.sh../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-selftest.sh../../../../skills/J-peer-review-and-audit/test-writer/skill/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/codex-coder/overlay/claude/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/codex-coder/overlay/claude/scripts/selftest/text-check.py../../../../skills/M-build-and-rollout/medic/skill/scripts/medic../../../../skills/M-build-and-rollout/medic/skill/scripts/medic.t../../../../skills/M-build-and-rollout/medic/skill/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/python-coder/skill/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/rust-coder/skill/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/shellscript-coder/skill/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/run-selftest.sh../../../../skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/text-check.py../../../../skills/M-build-and-rollout/ts-coder/skill/scripts/selftest/run-selftest.sh../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/adopt.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/adopt.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/agent-sessions.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/allowance-fallback.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/allowance-request-isolation.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/backend.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/calls.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/catalogue-cloud.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/catalogue.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/chunk.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-apply.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-batch.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-day.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-verdict.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-wait.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/config.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/evidence.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/first-message.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/harvest.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/harvest.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/hermes-openclaw.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/identity.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/identity.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/installed-roots.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/journey-adopt-lesson.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/journey-ops.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/labeler.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/labeler.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/ledger.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/lessons.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-filter.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-first-output.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-settings.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-writer.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/login-in-place.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/model-json.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/no-network.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/observe.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/page-journey.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/pages.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/pages.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer-loop.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer-validate.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall-hook.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/reflect.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/reflect.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/rem-reflect../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/rem-reflect.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/render-chunk.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/render.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/report.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/run-status.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/sampling.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/sampling.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest-guard.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/claude../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/codex../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/shim-core.cjs../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/sno../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/journey-e2e.sh../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/journey.mjs../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/observe-journey.mjs../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/run-selftest.sh../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/spawn-python.mjs../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/session.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/session.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/signal-local.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/skill-impact.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/station-settings.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/store-memory.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/store.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/test-helpers.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/text.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/trigger.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/trigger.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/verdicts.test.ts../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/verdicts.ts../../../../skills/S-communication-and-handoff/handoff/skill/scripts/handoff-checkpoint../../../../skills/S-communication-and-handoff/handoff/skill/scripts/handoff-checkpoint.t../../../../skills/S-communication-and-handoff/handoff/skill/scripts/selftest/run-selftest.sh../../../../skills/S-communication-and-handoff/handoff/skill/scripts/selftest/text-check.py../../../../skills/S-communication-and-handoff/heartbeat/skill/scripts/selftest/run-selftest.sh../../../../skills/S-communication-and-handoff/heartbeat/skill/scripts/selftest/text-check.py../../../../skills/S-communication-and-handoff/join-talk/skill/scripts/join-talk.sh../../../../skills/S-communication-and-handoff/join-talk/skill/scripts/selftest/run-selftest.sh../../../../skills/S-communication-and-handoff/reach/skill/scripts/selftest/run-selftest.sh../../../../skills/S-communication-and-handoff/reach/skill/scripts/selftest/text-check.py../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-answer-provider../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-preflight../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-resume../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-resume.t../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-switch../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-watch../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/fake-quota../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/run-selftest.sh../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/switch-provider.t../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/scripts/selftest/run-selftest.sh../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/scripts/selftest/text-check.py../../../../skills/T-delegation-and-work-orders/charter/skill/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos-evolve/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos-evolve/scripts/selftest/text-check.py../../../../skills/T-delegation-and-work-orders/cos/skills/cos-review/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos-review/scripts/selftest/text-check.py../../../../skills/T-delegation-and-work-orders/cos/skills/cos-watch/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos-watch/scripts/selftest/text-check.py../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-claim.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-claim.t../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.t../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-screen.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-screen.t../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-since.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-sentinel.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-sentinel.t../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-tree-check.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/selftest/text-check.py../../../../skills/T-delegation-and-work-orders/deliver/skill/scripts/deliver-proof../../../../skills/T-delegation-and-work-orders/deliver/skill/scripts/deliver-proof.t../../../../skills/T-delegation-and-work-orders/deliver/skill/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl-analyze/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl-audit/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl-dispatch/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl-env/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl-watch/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/agent-cli-help.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/attempt-gate.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/attempt-gate.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign-transfer-e2e.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign-worktree.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/convergence-watch.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/core-structure.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/docker-env-doctor.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-sentinel.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-sentinel.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-state.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-state.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-trust.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-trust.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/executor-wall.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/executor-wall.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/fence-check.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/gpu-watch.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/gpu-watch.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-open.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-open.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-resolve.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-resolve.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/log-watch.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/log-watch.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/on-station-proof.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/portable-paths.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster-git.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster-reach.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/script-running.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/script-running.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/selftest/run-selftest.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-generation-e2e.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-help.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-interactive-e2e.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-lane-resolve.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-mission-state-e2e.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-on-station-e2e.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-operate.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo-close-evidence.t../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo.sh../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo.t
Files
../../../../.claude-plugin/marketplace.jsonasset3,520 bytes../../.claude-plugin/icon.pngasset12,624 bytes../../.claude-plugin/plugin.jsonasset718 bytesSKILL.mdcore6,794 bytesSKILL.mdcore6,794 bytesscripts/selftest/run-selftest.shruns1,240 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.mddoc38,330 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/references/VALIDATION-REPORT.mddoc491 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/references/case-table.mddoc2,104 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/references/train-set.tsvasset6,148 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/references/unit-rates.mddoc8,069 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/calibration.truns789 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/run-selftest.shruns1,706 bytes../../../../skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/time-leftruns9,082 bytes../../../../skills/H-reporting-and-visibility/away-brief/skill/SKILL.mddoc3,476 bytes../../../../skills/H-reporting-and-visibility/away-brief/skill/scripts/away-briefruns12,552 bytes../../../../skills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.truns16,489 bytes../../../../skills/H-reporting-and-visibility/away-brief/skill/scripts/selftest/run-selftest.shruns1,297 bytes../../../../skills/H-reporting-and-visibility/catch-report/skill/SKILL.mddoc4,146 bytes../../../../skills/H-reporting-and-visibility/catch-report/skill/scripts/catch-reportruns28,187 bytes../../../../skills/H-reporting-and-visibility/catch-report/skill/scripts/catch-report.truns30,948 bytes../../../../skills/H-reporting-and-visibility/catch-report/skill/scripts/selftest/run-selftest.shruns1,747 bytes../../../../skills/J-peer-review-and-audit/agentic-walkthrough/skill/SKILL.mddoc6,794 bytes../../../../skills/J-peer-review-and-audit/agentic-walkthrough/skill/scripts/selftest/run-selftest.shruns1,240 bytes../../../../skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight/SKILL.mddoc12,414 bytes../../../../skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight/scripts/selftest/run-selftest.shruns1,164 bytes../../../../skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage/SKILL.mddoc5,710 bytes../../../../skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage/scripts/selftest/run-selftest.shruns1,196 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/SKILL.mddoc6,012 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/agents/openai.yamlasset353 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/references/report-contract.mddoc3,239 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/extract-prd-handoff.pyruns1,112 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/fixtures/expected-handoff.jsonasset1,928 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/fixtures/scenarios/inherited-constraint-test-first.mddoc2,134 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/fixtures/scenarios/raw-idea-reframe.mddoc2,126 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/fixtures/scenarios/sound-design-proceed.mddoc2,091 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/fixtures/target-prd.mddoc347 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/fixtures/valid-report.mddoc4,037 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-extractor-test.shruns1,955 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-scenarios.shruns3,290 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-selftest.shruns5,016 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/verify-manual-only.shruns2,848 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/verify-workflow-policy.shruns1,858 bytes../../../../skills/J-peer-review-and-audit/first-principles-review/skill/scripts/validate-report.pyruns9,873 bytes../../../../skills/J-peer-review-and-audit/less-is-more/skill/SKILL.mddoc6,612 bytes../../../../skills/J-peer-review-and-audit/less-is-more/skill/scripts/selftest/run-selftest.shruns1,662 bytes../../../../skills/J-peer-review-and-audit/owner-intent-audit/skill/SKILL.mddoc6,965 bytes../../../../skills/J-peer-review-and-audit/owner-intent-audit/skill/scripts/selftest/run-selftest.shruns154 bytes../../../../skills/J-peer-review-and-audit/owner-intent-audit/skill/scripts/selftest/verify-review-boundary.shruns920 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/SKILL.mddoc33,452 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/agents/openai.yamlasset216 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/assets/adversarial-plan-review.prompt.mddoc11,315 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/assets/adversarial-review.prompt.mddoc12,249 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/assets/adversarial-test-review.prompt.mddoc3,617 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/references/code-layers.mddoc5,490 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/references/doc-layers.mddoc5,598 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/references/python-advanced-patterns.mddoc7,962 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/references/python-standards.mddoc8,517 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/references/ts-standards.mddoc7,299 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/lib/sno-model.shruns1,490 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/review-backfill.shruns4,716 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/review-findings.shruns11,967 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/review-receipt.shruns5,384 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/run-adversarial-review.shruns58,475 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/cursor-process-group.truns2,094 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-cross-vendor.shruns14,842 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-model-settings.shruns5,179 bytes../../../../skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-selftest.shruns38,745 bytes../../../../skills/J-peer-review-and-audit/test-writer/skill/SKILL.mddoc5,717 bytes../../../../skills/J-peer-review-and-audit/test-writer/skill/references/eval-sim-patterns.mddoc8,688 bytes../../../../skills/J-peer-review-and-audit/test-writer/skill/scripts/selftest/run-selftest.shruns874 bytes../../../../skills/M-build-and-rollout/codex-coder/overlay/claude/SKILL.mddoc10,537 bytes../../../../skills/M-build-and-rollout/codex-coder/overlay/claude/scripts/selftest/run-selftest.shruns212 bytes../../../../skills/M-build-and-rollout/codex-coder/overlay/claude/scripts/selftest/text-check.pyruns1,744 bytes../../../../skills/M-build-and-rollout/medic/skill/SKILL.mddoc3,787 bytes../../../../skills/M-build-and-rollout/medic/skill/scripts/medicruns9,439 bytes../../../../skills/M-build-and-rollout/medic/skill/scripts/medic.truns10,543 bytes../../../../skills/M-build-and-rollout/medic/skill/scripts/selftest/run-selftest.shruns1,369 bytes../../../../skills/M-build-and-rollout/python-coder/skill/SKILL.mddoc7,427 bytes../../../../skills/M-build-and-rollout/python-coder/skill/references/advanced-patterns.mddoc8,777 bytes../../../../skills/M-build-and-rollout/python-coder/skill/scripts/selftest/run-selftest.shruns1,277 bytes../../../../skills/M-build-and-rollout/rust-coder/skill/SKILL.mddoc3,875 bytes../../../../skills/M-build-and-rollout/rust-coder/skill/agents/openai.yamlasset236 bytes../../../../skills/M-build-and-rollout/rust-coder/skill/references/standards.mddoc17,490 bytes../../../../skills/M-build-and-rollout/rust-coder/skill/scripts/selftest/run-selftest.shruns1,355 bytes../../../../skills/M-build-and-rollout/shellscript-coder/skill/SKILL.mddoc7,617 bytes../../../../skills/M-build-and-rollout/shellscript-coder/skill/scripts/selftest/run-selftest.shruns1,326 bytes../../../../skills/M-build-and-rollout/sno-cli/skill/SKILL.mddoc7,705 bytes../../../../skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/run-selftest.shruns297 bytes../../../../skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/text-check.pyruns4,034 bytes../../../../skills/M-build-and-rollout/ts-coder/skill/SKILL.mddoc5,545 bytes../../../../skills/M-build-and-rollout/ts-coder/skill/scripts/selftest/run-selftest.shruns1,201 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/SKILL.mddoc14,407 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/labeler.mddoc1,216 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/labeler.schema.jsonasset1,710 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/local-settings.jsonasset126 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/local-writer.schema.jsonasset2,400 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/proposal.schema.jsonasset3,265 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/render.jsonasset245 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/signals.jsonasset71 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/references/text.jsonasset4,106 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/adopt.test.tsruns13,355 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/adopt.tsruns14,657 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/agent-sessions.tsruns9,268 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/allowance-fallback.test.tsruns16,340 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/allowance-request-isolation.test.tsruns7,301 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/backend.tsruns9,338 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/calls.tsruns8,800 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/catalogue-cloud.test.tsruns1,485 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/catalogue.tsruns3,299 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/chunk.tsruns2,126 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-apply.test.tsruns25,825 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-batch.test.tsruns11,423 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-day.test.tsruns7,002 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-verdict.test.tsruns12,410 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-wait.test.tsruns1,348 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud.tsruns25,002 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/config.tsruns8,293 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.test.tsruns16,108 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.tsruns6,898 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/evidence.tsruns1,583 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/first-message.test.tsruns10,531 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/harvest.test.tsruns16,885 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/harvest.tsruns23,157 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/hermes-openclaw.test.tsruns26,179 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/identity.test.tsruns3,336 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/identity.tsruns3,571 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/installed-roots.test.tsruns11,277 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/journey-adopt-lesson.test.tsruns4,242 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/journey-ops.test.tsruns7,655 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/labeler.test.tsruns3,644 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/labeler.tsruns9,764 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/ledger.tsruns2,200 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/lessons.tsruns4,797 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-filter.test.tsruns3,995 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-first-output.test.tsruns22,598 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-settings.tsruns1,457 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-writer.tsruns12,903 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/login-in-place.test.tsruns5,944 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/model-json.tsruns4,209 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/no-network.test.tsruns5,162 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/observe.tsruns1,466 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/page-journey.test.tsruns6,810 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/pages.test.tsruns4,243 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/pages.tsruns4,894 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer-loop.test.tsruns1,503 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer-validate.test.tsruns9,355 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer.tsruns8,864 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall-hook.test.tsruns21,376 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall.test.tsruns32,149 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall.tsruns18,613 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/reflect.test.tsruns9,472 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/reflect.tsruns14,624 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/rem-reflectruns823 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/rem-reflect.tsruns18,198 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/render-chunk.test.tsruns7,353 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/render.tsruns9,890 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/report.tsruns8,380 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/run-status.test.tsruns19,586 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/sampling.test.tsruns2,164 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/sampling.tsruns915 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest-guard.test.tsruns4,089 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/clauderuns94 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/codexruns93 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/shim-core.cjsruns4,705 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/snoruns5,818 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/fixtures/hermes-session-export.jsonlasset1,498 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/fixtures/openclaw-events.jsonlasset3,793 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/fixtures/verdict-traces.jsonasset16,989 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/journey-e2e.shruns1,384 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/journey.mjsruns9,740 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/observe-journey.mjsruns12,800 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/run-selftest.shruns6,770 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/spawn-python.mjsruns765 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/session.test.tsruns5,251 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/session.tsruns251 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/signal-local.test.tsruns7,207 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/skill-impact.test.tsruns6,313 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/station-settings.test.tsruns13,977 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/store-memory.test.tsruns3,522 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/store.tsruns7,917 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/test-helpers.tsruns15,672 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/text.tsruns760 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/trigger.test.tsruns3,726 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/trigger.tsruns2,587 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/verdicts.test.tsruns8,284 bytes../../../../skills/R-recursive-self-improvement/rem-reflect/skill/scripts/verdicts.tsruns8,179 bytes../../../../skills/S-communication-and-handoff/handoff/skill/SKILL.mddoc18,773 bytes../../../../skills/S-communication-and-handoff/handoff/skill/references/reach-contract.jsonasset1,431 bytes../../../../skills/S-communication-and-handoff/handoff/skill/scripts/handoff-checkpointruns9,557 bytes../../../../skills/S-communication-and-handoff/handoff/skill/scripts/handoff-checkpoint.truns8,140 bytes../../../../skills/S-communication-and-handoff/handoff/skill/scripts/selftest/run-selftest.shruns167 bytes../../../../skills/S-communication-and-handoff/handoff/skill/scripts/selftest/text-check.pyruns12,968 bytes../../../../skills/S-communication-and-handoff/heartbeat/skill/SKILL.mddoc12,327 bytes../../../../skills/S-communication-and-handoff/heartbeat/skill/references/heartbeat-contract.jsonasset363 bytes../../../../skills/S-communication-and-handoff/heartbeat/skill/scripts/selftest/run-selftest.shruns204 bytes../../../../skills/S-communication-and-handoff/heartbeat/skill/scripts/selftest/text-check.pyruns4,910 bytes../../../../skills/S-communication-and-handoff/join-talk/skill/SKILL.mddoc2,787 bytes../../../../skills/S-communication-and-handoff/join-talk/skill/scripts/join-talk.shruns4,556 bytes../../../../skills/S-communication-and-handoff/join-talk/skill/scripts/selftest/run-selftest.shruns7,031 bytes../../../../skills/S-communication-and-handoff/reach/skill/SKILL.mddoc10,572 bytes../../../../skills/S-communication-and-handoff/reach/skill/references/reach-contract.jsonasset1,394 bytes../../../../skills/S-communication-and-handoff/reach/skill/scripts/selftest/run-selftest.shruns130 bytes../../../../skills/S-communication-and-handoff/reach/skill/scripts/selftest/text-check.pyruns7,984 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/SKILL.mddoc13,204 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-answer-providerruns3,972 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-preflightruns7,804 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-resumeruns12,955 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-resume.truns10,121 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-switchruns5,242 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-watchruns6,767 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/fake-quotaruns267 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/run-selftest.shruns9,366 bytes../../../../skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/switch-provider.truns16,035 bytes../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/SKILL.mddoc8,377 bytes../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/references/heartbeat-contract.jsonasset363 bytes../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/references/subscription-quota-check-contract.jsonasset342 bytes../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/scripts/selftest/run-selftest.shruns204 bytes../../../../skills/S-communication-and-handoff/subscription-quota-check/skill/scripts/selftest/text-check.pyruns6,400 bytes../../../../skills/T-delegation-and-work-orders/charter/skill/SKILL.mddoc4,835 bytes../../../../skills/T-delegation-and-work-orders/charter/skill/references/questions.mddoc847 bytes../../../../skills/T-delegation-and-work-orders/charter/skill/references/template.mddoc2,447 bytes../../../../skills/T-delegation-and-work-orders/charter/skill/scripts/selftest/run-selftest.shruns1,561 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-evolve/SKILL.mddoc15,514 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-evolve/scripts/selftest/run-selftest.shruns204 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-evolve/scripts/selftest/text-check.pyruns1,059 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-review/SKILL.mddoc12,990 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-review/scripts/selftest/run-selftest.shruns204 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-review/scripts/selftest/text-check.pyruns1,215 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-watch/SKILL.mddoc12,992 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-watch/scripts/selftest/run-selftest.shruns204 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos-watch/scripts/selftest/text-check.pyruns1,073 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/LEARNING.mddoc6,232 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/SKILL.mddoc77,869 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/references/card-template.mddoc11,124 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/references/digest-template.mddoc4,986 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/references/owner-profile.mddoc5,426 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/references/pocket-card.mddoc1,590 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-claim.shruns30,176 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-claim.truns12,698 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.shruns41,501 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.truns7,157 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-screen.shruns4,902 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-screen.truns2,546 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-since.shruns3,703 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-sentinel.shruns6,157 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-sentinel.truns2,479 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-tree-check.shruns2,687 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/selftest/run-selftest.shruns204 bytes../../../../skills/T-delegation-and-work-orders/cos/skills/cos/scripts/selftest/text-check.pyruns1,036 bytes../../../../skills/T-delegation-and-work-orders/deliver/skill/SKILL.mddoc5,861 bytes../../../../skills/T-delegation-and-work-orders/deliver/skill/references/proof.mddoc1,806 bytes../../../../skills/T-delegation-and-work-orders/deliver/skill/scripts/deliver-proofruns6,216 bytes../../../../skills/T-delegation-and-work-orders/deliver/skill/scripts/deliver-proof.truns13,182 bytes../../../../skills/T-delegation-and-work-orders/deliver/skill/scripts/selftest/run-selftest.shruns1,729 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-analyze/SKILL.mddoc6,271 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-analyze/scripts/selftest/run-selftest.shruns1,169 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-audit/SKILL.mddoc14,554 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-audit/scripts/selftest/run-selftest.shruns1,182 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-dispatch/SKILL.mddoc31,860 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-dispatch/scripts/selftest/run-selftest.shruns1,218 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-env/SKILL.mddoc7,328 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-env/scripts/selftest/run-selftest.shruns1,150 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-watch/SKILL.mddoc28,456 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl-watch/scripts/selftest/run-selftest.shruns1,231 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/SKILL.mddoc63,182 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/references/callsigns.txtdoc384 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/references/decision-rights.mddoc4,918 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/references/dispatch-template.mddoc39,095 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/references/pocket-card.mddoc1,922 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/references/progress-reporting-hooks.mddoc2,367 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/references/todo-template.mddoc7,030 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/agent-cli-help.truns1,276 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/attempt-gate.shruns3,701 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/attempt-gate.truns4,701 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign-transfer-e2e.shruns8,051 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign-worktree.truns1,763 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign.shruns15,459 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/convergence-watch.shruns8,781 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/core-structure.truns5,884 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/docker-env-doctor.shruns19,505 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-sentinel.shruns5,872 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-sentinel.truns2,481 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-state.shruns19,605 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-state.truns22,541 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-trust.shruns5,469 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-trust.truns6,508 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/executor-wall.shruns6,781 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/executor-wall.truns9,041 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/fence-check.shruns4,511 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.shruns13,850 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.truns5,986 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/gpu-watch.shruns4,645 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/gpu-watch.truns1,521 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-open.shruns4,060 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-open.truns3,952 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-resolve.shruns5,119 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-resolve.truns6,959 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/log-watch.shruns11,145 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/log-watch.truns6,953 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/on-station-proof.truns1,730 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/portable-paths.truns1,546 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster-git.truns4,169 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster-reach.truns2,853 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster.shruns20,354 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/script-running.shruns3,481 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/script-running.truns3,809 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/selftest/run-selftest.shruns1,231 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-generation-e2e.shruns1,963 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-help.truns2,898 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-interactive-e2e.shruns13,550 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-lane-resolve.truns3,502 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-mission-state-e2e.shruns1,801 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-on-station-e2e.shruns2,286 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-operate.truns9,457 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec.shruns37,639 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo-close-evidence.truns1,211 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo.shruns36,369 bytes../../../../skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo.truns28,474 bytes
Read SKILL.md
# Agentic Walkthrough — take the program's seat
The stance is the whole method. You are not a reviewer standing outside the code with a
checklist; you are the thing the source describes — the job, the stage, the handler — and
you run it in your head, hop by hop, exactly as it would run, noticing every switch you pass
and every place your output goes. Only then do you turn to the real system and make it show
you that what you just walked actually happened. The principle: BE the executor, then make the
executor prove itself.
Ordinary debugging starts from a failure — an error, a red test, a wrong number. This starts from
the opposite and much quieter case: **everything reports success and you still do not know whether
the work happened.**
That case is real and it is not rare. A stage that cannot do its work can still report `done`. Acharter
When your agent uses it
Write, revise or review a charter: the one document that tells an executor what to deliver, what is out of bounds, what the owner already decided, and how each success check will be proven. Use when work needs a written brief before someone else does it, or when asked to write, change or check a charter.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,074 tokensWhen the skill is activated
Reference documents
766 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Rules that keep a charter useful
- Write
- Revise
- Review only
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesreferences/questions.mddoc847 bytesreferences/template.mddoc2,447 bytesscripts/selftest/run-selftest.shruns1,561 bytes
Read SKILL.md
# charter
A charter is one markdown file that says what to deliver and how everyone will know it was
delivered. A task is named by its charter
filename. `charter` writes it; `deliver` carries a released charter out. Any kind of project
uses it: software, documents, campaigns, research, operations. The owner is whoever owns the
work (often the user); speak to them in the language they use.
Prerequisites: none to use it; its selftest needs bash and python3.
Read `references/template.md` for the file layout and `references/questions.md` before asking
the owner anything.
## Rules that keep a charter usefule2e-environment-preflight
When your agent uses it
Check external services, hosts, browser sessions, model endpoints, and agents before an end-to-end run. MANUAL-ONLY: load when a caller names it. NEVER auto-load from context for ordinary testing or debugging.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,776 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 trigger, as an operational test
- Why this exists
- Two stages, in this order
- Artifact 1 — the system primer
- Artifact 2 — the runner
- Artifact 3 — the red scoreboard
- Anti-patterns — any one fails the gate
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore12,414 bytesSKILL.mdcore12,414 bytesscripts/selftest/run-selftest.shruns1,164 bytes
Read SKILL.md
# e2e-environment-preflight — the gate that runs before the first row
**Never auto-triggered.** Named callers only:
| Caller | Moment |
|---|---|
| A requirements document or test plan | once end-to-end proof is required and the document names an external system |
| A task brief | before staffing any end-to-end journey |
| `e2e-red-triage` | when a red turns out to be environmental and owes a new check |
This skill is self-contained: the trigger and the three artifacts.
Terms: the **owner** is whoever owns the work, usually the user; a **row** is one acceptance check in the test plan; a **journey** is one end-to-end scenario made of rows; a **red** is a row that failed or gave no answer; the **suite** is all the rows of a journey.
e2e-red-triage
When your agent uses it
Classify one unexpected end-to-end test failure as a product defect or an environment fault needing a new preflight check. MANUAL-ONLY: load when the suite runner names a specific failure. NEVER auto-load from context.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,331 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
- Why this needs its own protocol
- The three moves, in order
- Classify before you close
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,710 bytesSKILL.mdcore5,710 bytesscripts/selftest/run-selftest.shruns1,196 bytes
Read SKILL.md
# e2e-red-triage — for the reds the preflight could not have predicted
Terms are as in `e2e-environment-preflight`: a **row** is one acceptance check in the test plan, a **red** is a row that failed or gave no answer, a **journey** is one end-to-end scenario made of rows, the **suite** is all the rows of a journey, and **preflight** is the set of environment checks that must be green before the first row runs.
**Never auto-triggered, and normally never needed.** One caller — the agent running the suite —
and one moment:
> The `e2e-environment-preflight` checks were **all green**, and a row went **red anyway** — or produced a
> null, an empty, a zero, or a silence nobody can yet explain.
If preflight was not green, the suite should not have started. If a red is an ordinary product
failure with a clear cause, fix it and move on; this is not the ceremony for an ordinary bug.
This is the residual after the gate has done its work — a small fraction, and one
that shrinks every time move 3 is honoured.first-principles-review
When your agent uses it
MANUAL-ONLY: challenge a product idea, design, PRD, or architecture from first principles. Use only when the user names this skill. Research first, then write a local review and PRD handoff.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,319 tokensWhen the skill is activated
Reference documents
2,916 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Invocation Gate
- Workflow
- Judgment Rules
- Output
Scripts executed separately
scripts/extract-prd-handoff.pyscripts/selftest/run-extractor-test.shscripts/selftest/run-scenarios.shscripts/selftest/run-selftest.shscripts/selftest/verify-manual-only.shscripts/selftest/verify-workflow-policy.shscripts/validate-report.py
Files
SKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesagents/openai.yamlasset353 bytesreferences/report-contract.mddoc3,239 bytesscripts/extract-prd-handoff.pyruns1,112 bytesscripts/selftest/fixtures/expected-handoff.jsonasset1,928 bytesscripts/selftest/fixtures/scenarios/inherited-constraint-test-first.mddoc2,134 bytesscripts/selftest/fixtures/scenarios/raw-idea-reframe.mddoc2,126 bytesscripts/selftest/fixtures/scenarios/sound-design-proceed.mddoc2,091 bytesscripts/selftest/fixtures/target-prd.mddoc347 bytesscripts/selftest/fixtures/valid-report.mddoc4,037 bytesscripts/selftest/run-extractor-test.shruns1,955 bytesscripts/selftest/run-scenarios.shruns3,290 bytesscripts/selftest/run-selftest.shruns5,016 bytesscripts/selftest/verify-manual-only.shruns2,848 bytesscripts/selftest/verify-workflow-policy.shruns1,858 bytesscripts/validate-report.pyruns9,873 bytes
Read SKILL.md
# First-Principles Reviewer
Run before a proposal hardens into requirements or source code. The owner is whoever owns the
work and decides what it should be; often that is the user. A PRD is a product requirements
document. Judge the problem framing,
constraints, and solution shape. Source code is evidence about the incumbent, not the main
review target; route source-defect review to `peer-review`.
## Invocation Gate
Proceed only when the human explicitly invokes this skill (`$first-principles-review` or
`/first-principles-review`) or names it in the current request. Do not infer invocation from the presence of a PRD or design.
## Workflowless-is-more
When your agent uses it
Write the least code that works, and cut what an AI agent over-built. Use on any coding task: write, fix, refactor, or review a diff. Also when the user says 'less', 'simplify', 'too complex', 'over-engineered', or 'what can we delete'. Not for prose, research, or non-code questions.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,459 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
- Delete these first
- Tests spend the development budget
- Build: climb the ladder before writing
- Cut: look back after writing
- Keep only what the task needs
- Boundaries
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore6,612 bytesSKILL.mdcore6,612 bytesscripts/selftest/run-selftest.shruns1,662 bytes
Read SKILL.md
# Less is more
The best code is the code never written. "Owner" below means whoever owns the work, usually the user.
**Mode picks itself from the verb.** Asked to write, add, fix, or refactor → **build**.
Asked to review, simplify, or say what can be deleted → **cut**. After build, run cut on the
code you just wrote before handing it over. A mode the user names wins.
Read first, then be lazy. Trace every file the change touches and the real flow end to end.
A small diff in the wrong place is a second bug, not laziness.
## Delete these first
By default, security checks, blocking preconditions, runtime assertions, and hashes are priorityowner-intent-audit
When your agent uses it
Check agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work, stale truth, unreachable decisions, unsupported completion claims, and implementation debt. Use before approval or merge.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,490 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
- What must be established
- Evidence and judgment boundaries
- Output
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/verify-review-boundary.sh
Files
SKILL.mdcore6,965 bytesSKILL.mdcore6,965 bytesscripts/selftest/run-selftest.shruns154 bytesscripts/selftest/verify-review-boundary.shruns920 bytes
Read SKILL.md
# Owner Intent Audit
The question this review answers is not "is the artifact good" but **"is this what the owner
meant, and what did the agent leave behind while making it?"** (The owner is whoever owns the
work and decides what it should be; often that is the user.) An agent can produce a PRD (product
requirements document), a plan, or a diff that is locally excellent and still specify a different product, carry work
nobody asked for, or hide the debts agents characteristically create. Reviewing the artifact
for its own defects — bugs, security holes, silent death — is peer-review's job, not this one;
the two are run separately and neither substitutes for the other.
- **Plan mode:** PRDs, designs, specs, task lists, refactor plans, and test plans.
- **Code mode:** diffs, files, tests, or subsystems substantially written by agents.
Start with the ordinary user and system flow. Realistic common-path failure outranks exoticpython-coder
When your agent uses it
Implement and refactor production Python, FastAPI, Pydantic, async, and migrations.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,601 tokensWhen the skill is activated
Reference documents
2,043 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Runtime Source of Truth
- Boundaries
- Design Rules
- Verification
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore7,427 bytesSKILL.mdcore7,427 bytesreferences/advanced-patterns.mddoc8,777 bytesscripts/selftest/run-selftest.shruns1,277 bytes
Read SKILL.md
# Python Coder
Every development task has a finite budget including setup, tests, and reporting.
Before running tests, estimate duration from available timings and identify the changed
behavior or directly affected consumer. If timing is unknown, state an estimate; do not
build a timing system or run a preliminary suite. Full evaluation, unit, integration,
or repository suites require the owner's explicit request, never a skill, PRD, review,
or default command. Remove checks that neither prove the requested main function nor
expose its defects. Repeat only after a relevant change or failure.
Every new security check requires the owner's explicit approval for that specific check;
remove auxiliary security, assertion, hash, or bookkeeping blockers of useful work.
Write production Python that fits the current repository, stays small, and is easy to verify. Local repo instructions add project-specific detail; they do not weaken these rules.rust-coder
When your agent uses it
Implement, refactor, and migrate production Rust with repository-grounded ownership, type-driven invariants, explicit errors, safe concurrency, minimal unsafe code, and verified Cargo workflows. Use for Rust features, crates, CLIs, services, libraries, async code, FFI, performance work, migrations, or substantial .rs and Cargo.toml changes, including requests such as 'rust-coder', 'write Rust', or 'implement this Rust feature with Codex'.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
795 tokensWhen the skill is activated
Reference documents
3,512 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inspect
- Design and implement
- Verify
- Report
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore3,875 bytesagents/openai.yamlasset236 bytesreferences/standards.mddoc17,490 bytesscripts/selftest/run-selftest.shruns1,355 bytes
Read SKILL.md
# Rust Coder
Implement directly in the current Codex session. Do not launch another Codex process.
Read [references/standards.md](references/standards.md) completely before editing. Repository instructions and the declared toolchain override generic preferences.
## Inspect
Read the smallest complete set of evidence:
- Nearest `AGENTS.md`, `CLAUDE.md`, and repository instructions.
- Root and target `Cargo.toml`, `Cargo.lock`, `rust-toolchain*`, Cargo configuration, lint and format configuration, features, targets, and continuous-integration commands.
- Every target file in full, its parent exports, immediate callers, traits, types, errors, feature gates, platform boundaries, focused tests, and one or two tested sibling modules.
- The exact format, check, test, Clippy, feature, and target commands used by the crate.shellscript-coder
When your agent uses it
Implement and refactor production shell scripts, command-line tools, automation, process wrappers, and Git or infrastructure helpers with reliable failures, useful logs, and machine-readable output.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,494 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
- Read Before Writing
- Boundaries
- Reliability
- Messages and Agent-Facing Interfaces
- Failure Design
- Verification
- Delivery
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore7,617 bytesscripts/selftest/run-selftest.shruns1,326 bytes
Read SKILL.md
# Shell Script Coder
Every development task has a finite budget including setup, tests, and reporting.
Before running tests, estimate duration from available timings and identify the changed
behavior or directly affected consumer. If timing is unknown, state an estimate; do not
build a timing system or run a preliminary suite. Full evaluation, unit, integration,
or repository suites require the owner's explicit request, never a skill, PRD, review,
or default command. Remove checks that neither prove the requested main function nor
expose its defects. Repeat only after a relevant change or failure.
Every new security check requires the owner's explicit approval for that specific check;
remove auxiliary security, assertion, hash, or bookkeeping blockers of useful work.
Write small, production-grade Bash that fits the repository and remains understandable during failure. Local instructions define the runtime and style; they may strengthen these rules but not weaken reliability.test-writer
When your agent uses it
Write and improve test-owned code: tests, test scripts, fixtures, evals, and test-only helpers. Use whenever Codex is asked to create or change test code. Its only job is to produce the strongest practical tests in the repository's existing harness, run them, and fix defects in the test code.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,173 tokensWhen the skill is activated
Reference documents
1,993 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Test scope
- Single responsibility
- Core principles
- Test ownership
- Write the code
- Test quality
- Optional code references
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,717 bytesreferences/eval-sim-patterns.mddoc8,688 bytesscripts/selftest/run-selftest.shruns874 bytes
Read SKILL.md
# Test Writer
Write the best test code for the requested behavior. Start with the repository and the
behavior.
## Test scope
- Run tests only for the changed behavior and its directly affected callers or integrations.
- Do not run full evaluation, unit, integration, repository, site, or all-module suites unless the owner explicitly requests them.
- A skill, PRD, reviewer, repository document, or default package script does not grant that permission.
- After a failure, rerun the failing case first. Once it passes, run only directly affected cases; do not expand by default.
- Build artifacts required for a requested deployment are not permission to run unrelated tests.
- Every development task has a finite budget including setup, execution, and reporting; before each run, estimate duration from available timings and name the changed behavior it verifies, using a stated estimate when timings are unknown rather than building a timing system or running a preliminary suite.
- Remove checks and repeated runs that neither establish the requested main function nor expose its defects; select the smallest useful test that fits the remaining development budget, never spend it on reassurance.ts-coder
When your agent uses it
Implement and refactor production TypeScript/TSX, strict types, APIs, and migrations.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,083 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
- Boundaries
- Standards
- Migrations
- Verification
- Delivery
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,545 bytesSKILL.mdcore5,545 bytesscripts/selftest/run-selftest.shruns1,201 bytes
Read SKILL.md
# TypeScript Coder
Every development task has a finite budget including setup, tests, and reporting.
Before running tests, estimate duration from available timings and identify the changed
behavior or directly affected consumer. If timing is unknown, state an estimate; do not
build a timing system or run a preliminary suite. Full evaluation, unit, integration,
or repository suites require the owner's explicit request, never a skill, PRD, review,
or default command. Remove checks that neither prove the requested main function nor
expose its defects. Repeat only after a relevant change or failure.
Every new security check requires the owner's explicit approval for that specific check;
remove auxiliary security, assertion, hash, or bookkeeping blockers of useful work.
Write TypeScript that fits the current repository, stays small, and is easy to verify. Local repo instructions add project-specific detail; they do not weaken these rules.agentic-time-estimate
When your agent uses it
Answer how long agent work will take, how much longer active work needs, or what clock time applies. Estimate full AI-agent wall time, measure active progress first, and get owner-facing times from `sno report-time`. Never estimate human-developer time.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
9,529 tokensWhen the skill is activated
Reference documents
2,628 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Clock times for the owner — the `sno report-time` command
- How much longer — work already in flight
- The estimator
- Step 1 — Extract countables (deterministic schema)
- Step 2 — Rounds (agent-active work)
- Step 3 — Four disjoint clocks (minutes; each event in exactly one clock)
- Step 4 — PERT (closed form)
- Step 4b — Scope-expansion multiplier (mandatory)
- Step 5 — Anchor shrinkage (never hard override)
- Step 5b — Owner-wait line (separate; never touches the agent clocks)
- Step 6 — Output (chat block + one JSON line)
- Boundaries
- Rationalizations — pre-refuted
Scripts executed separately
scripts/selftest/calibration.tscripts/selftest/run-selftest.shscripts/time-left
Files
SKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesSKILL.mdcore38,330 bytesreferences/VALIDATION-REPORT.mddoc491 bytesreferences/case-table.mddoc2,104 bytesreferences/train-set.tsvasset6,148 bytesreferences/unit-rates.mddoc8,069 bytesscripts/selftest/calibration.truns789 bytesscripts/selftest/run-selftest.shruns1,706 bytesscripts/time-leftruns9,082 bytes
Read SKILL.md
# Agent time — how long, how much longer, and what time it is
Before running the scripts below, set `AGENTIC_TIME_ESTIMATE_SKILL_DIR` to the absolute path of this skill's directory (the folder that holds this `SKILL.md`) in the same shell command.
**Prerequisites.** Linux with procps `ps` (with the `etimes` column) and `pgrep`, plus the `sno report-time` command from Sno Station; `sno report-time --pid` also needs `/proc` and GNU `date`. `time-left` stops with one clear message when they are missing.
"Owner" below means whoever owns the work and reads the answer, usually the user. A "journey" is one piece of delegated work from request to close. A "route card" is the record that dispatched it, and the "routing ledger" is a project file with one row per journey (the `pl` skill writes both when it is installed); every rule below that mentions them applies only when the project keeps them, and is skipped otherwise. A ledger's `closed` event and its fields (`anchor_key`, `actual_body_h`, `actual_process_h`, `calibration_note`) are defined by the `pl` skill; without a ledger, still emit `anchor_key` in the estimate, so a later close can copy it.
Three questions live here. **What clock time to write for the owner** is the
`sno report-time` command, immediately below. **How much longer** for work already running is
the in-flight section after it — measured facts first, judgment last. **How long** a fresh
piece of work will take is the estimator, everything from Step 1 down. All three are
answered from a script or a table before they are ever answered by thinking about it.
away-brief
When your agent uses it
Give the owner one page when they come back from sleep, a meeting or a long run: what got done, what is stuck, what waits for their answer, and what it cost in quota. Use when the owner asks what happened while they were away, wants a status page, or when you finish a long stretch of work and must report it.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
866 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
- Use
- What the page can and cannot say
Scripts executed separately
scripts/away-briefscripts/away-brief.tscripts/selftest/run-selftest.sh
Files
SKILL.mdcore3,476 bytesSKILL.mdcore3,476 bytesSKILL.mdcore3,476 bytesscripts/away-briefruns12,552 bytesscripts/away-brief.truns16,489 bytesscripts/selftest/run-selftest.shruns1,297 bytes
Read SKILL.md
# away-brief
`sno away-brief run` reads what already exists and prints one page of at most 60 lines. It changes nothing
except its own list of quota readings, and Reach, which may note that it has seen the cards that the inbox
read listed (it never moves, accepts or finishes them).
```
## Done new commits, charters delivered since the cutoff (with how many checks are proven),
progress records that finished or are still going
## Stuck charters not finished (with the numbers of the checks not yet proven), progress records
with tasks left that nobody has touched for two hours
## Needs you Reach cards of type question or decision waiting in the inbox
## Spend your heartbeats, and each vendor's quota now with the change since the last reading
```catch-report
When your agent uses it
Report how many problems the two brains found: mutual review (the other model checks the work, from the peer-review records) and self-check (an agent finds its own error in its own conversation, judged by that agent's own model), side by side. Use when the owner asks whether the second agent or the reviews are worth it, or wants the week's review results.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,004 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
- Use
Scripts executed separately
scripts/catch-reportscripts/catch-report.tscripts/selftest/run-selftest.sh
Files
SKILL.mdcore4,146 bytesSKILL.mdcore4,146 bytesSKILL.mdcore4,146 bytesscripts/catch-reportruns28,187 bytesscripts/catch-report.truns30,948 bytesscripts/selftest/run-selftest.shruns1,747 bytes
Read SKILL.md
# catch-report
The product claim is two brains: one does the work, another checks it. `sno catch-report` puts numbers on that
claim from records already on this machine. It changes nothing.
- **Mutual review** is every review the `peer-review` skill recorded: a different model read the work and
reported problems. `sno catch-report run` prints those numbers.
- **Self-check** is an agent finding its own error inside one conversation. `sno catch-report self` reads the
agents' own conversations (`~/.claude/projects`, `~/.codex/sessions`), picks the moments where an agent
reacted to a failing command or test, or admitted a mistake, and asks that agent's own model (claude
judges claude conversations, codex judges codex conversations) whether the agent found the error itself or
was told. It then prints the two side by side.
Prerequisites: bash 4+, GNU date, find and grep, and jq. `self` also needs the `claude` and/or `codex` commandagentic-walkthrough
When your agent uses it
Prove that a reported run caused its intended real effect. Walk the executor path from entry to effect, capture one observable per hop, and report a result a no-op could not produce.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,537 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
- 1. Walk the path — be the program, read, don't run
- 2. Probe every hop that has to be real
- 3. Report a number, not an impression
- Before any absence becomes a finding, check your instrument
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore6,794 bytesSKILL.mdcore6,794 bytesscripts/selftest/run-selftest.shruns1,240 bytes
Read SKILL.md
# Agentic Walkthrough — take the program's seat
The stance is the whole method. You are not a reviewer standing outside the code with a
checklist; you are the thing the source describes — the job, the stage, the handler — and
you run it in your head, hop by hop, exactly as it would run, noticing every switch you pass
and every place your output goes. Only then do you turn to the real system and make it show
you that what you just walked actually happened. The principle: BE the executor, then make the
executor prove itself.
Ordinary debugging starts from a failure — an error, a red test, a wrong number. This starts from
the opposite and much quieter case: **everything reports success and you still do not know whether
the work happened.**
That case is real and it is not rare. A stage that cannot do its work can still report `done`. Ae2e-environment-preflight
When your agent uses it
Check external services, hosts, browser sessions, model endpoints, and agents before an end-to-end run. MANUAL-ONLY: load when a caller names it. NEVER auto-load from context for ordinary testing or debugging.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,776 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 trigger, as an operational test
- Why this exists
- Two stages, in this order
- Artifact 1 — the system primer
- Artifact 2 — the runner
- Artifact 3 — the red scoreboard
- Anti-patterns — any one fails the gate
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore12,414 bytesSKILL.mdcore12,414 bytesscripts/selftest/run-selftest.shruns1,164 bytes
Read SKILL.md
# e2e-environment-preflight — the gate that runs before the first row
**Never auto-triggered.** Named callers only:
| Caller | Moment |
|---|---|
| A requirements document or test plan | once end-to-end proof is required and the document names an external system |
| A task brief | before staffing any end-to-end journey |
| `e2e-red-triage` | when a red turns out to be environmental and owes a new check |
This skill is self-contained: the trigger and the three artifacts.
Terms: the **owner** is whoever owns the work, usually the user; a **row** is one acceptance check in the test plan; a **journey** is one end-to-end scenario made of rows; a **red** is a row that failed or gave no answer; the **suite** is all the rows of a journey.
e2e-red-triage
When your agent uses it
Classify one unexpected end-to-end test failure as a product defect or an environment fault needing a new preflight check. MANUAL-ONLY: load when the suite runner names a specific failure. NEVER auto-load from context.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,331 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
- Why this needs its own protocol
- The three moves, in order
- Classify before you close
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,710 bytesSKILL.mdcore5,710 bytesscripts/selftest/run-selftest.shruns1,196 bytes
Read SKILL.md
# e2e-red-triage — for the reds the preflight could not have predicted
Terms are as in `e2e-environment-preflight`: a **row** is one acceptance check in the test plan, a **red** is a row that failed or gave no answer, a **journey** is one end-to-end scenario made of rows, the **suite** is all the rows of a journey, and **preflight** is the set of environment checks that must be green before the first row runs.
**Never auto-triggered, and normally never needed.** One caller — the agent running the suite —
and one moment:
> The `e2e-environment-preflight` checks were **all green**, and a row went **red anyway** — or produced a
> null, an empty, a zero, or a silence nobody can yet explain.
If preflight was not green, the suite should not have started. If a red is an ordinary product
failure with a clear cause, fix it and move on; this is not the ceremony for an ordinary bug.
This is the residual after the gate has done its work — a small fraction, and one
that shrinks every time move 3 is honoured.first-principles-review
When your agent uses it
MANUAL-ONLY: challenge a product idea, design, PRD, or architecture from first principles. Use only when the user names this skill. Research first, then write a local review and PRD handoff.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,319 tokensWhen the skill is activated
Reference documents
2,916 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Invocation Gate
- Workflow
- Judgment Rules
- Output
Scripts executed separately
scripts/extract-prd-handoff.pyscripts/selftest/run-extractor-test.shscripts/selftest/run-scenarios.shscripts/selftest/run-selftest.shscripts/selftest/verify-manual-only.shscripts/selftest/verify-workflow-policy.shscripts/validate-report.py
Files
SKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesSKILL.mdcore6,012 bytesagents/openai.yamlasset353 bytesreferences/report-contract.mddoc3,239 bytesscripts/extract-prd-handoff.pyruns1,112 bytesscripts/selftest/fixtures/expected-handoff.jsonasset1,928 bytesscripts/selftest/fixtures/scenarios/inherited-constraint-test-first.mddoc2,134 bytesscripts/selftest/fixtures/scenarios/raw-idea-reframe.mddoc2,126 bytesscripts/selftest/fixtures/scenarios/sound-design-proceed.mddoc2,091 bytesscripts/selftest/fixtures/target-prd.mddoc347 bytesscripts/selftest/fixtures/valid-report.mddoc4,037 bytesscripts/selftest/run-extractor-test.shruns1,955 bytesscripts/selftest/run-scenarios.shruns3,290 bytesscripts/selftest/run-selftest.shruns5,016 bytesscripts/selftest/verify-manual-only.shruns2,848 bytesscripts/selftest/verify-workflow-policy.shruns1,858 bytesscripts/validate-report.pyruns9,873 bytes
Read SKILL.md
# First-Principles Reviewer
Run before a proposal hardens into requirements or source code. The owner is whoever owns the
work and decides what it should be; often that is the user. A PRD is a product requirements
document. Judge the problem framing,
constraints, and solution shape. Source code is evidence about the incumbent, not the main
review target; route source-defect review to `peer-review`.
## Invocation Gate
Proceed only when the human explicitly invokes this skill (`$first-principles-review` or
`/first-principles-review`) or names it in the current request. Do not infer invocation from the presence of a PRD or design.
## Workflowless-is-more
When your agent uses it
Write the least code that works, and cut what an AI agent over-built. Use on any coding task: write, fix, refactor, or review a diff. Also when the user says 'less', 'simplify', 'too complex', 'over-engineered', or 'what can we delete'. Not for prose, research, or non-code questions.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,459 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
- Delete these first
- Tests spend the development budget
- Build: climb the ladder before writing
- Cut: look back after writing
- Keep only what the task needs
- Boundaries
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore6,612 bytesSKILL.mdcore6,612 bytesscripts/selftest/run-selftest.shruns1,662 bytes
Read SKILL.md
# Less is more
The best code is the code never written. "Owner" below means whoever owns the work, usually the user.
**Mode picks itself from the verb.** Asked to write, add, fix, or refactor → **build**.
Asked to review, simplify, or say what can be deleted → **cut**. After build, run cut on the
code you just wrote before handing it over. A mode the user names wins.
Read first, then be lazy. Trace every file the change touches and the real flow end to end.
A small diff in the wrong place is a second bug, not laziness.
## Delete these first
By default, security checks, blocking preconditions, runtime assertions, and hashes are priorityowner-intent-audit
When your agent uses it
Check agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work, stale truth, unreachable decisions, unsupported completion claims, and implementation debt. Use before approval or merge.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,490 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
- What must be established
- Evidence and judgment boundaries
- Output
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/verify-review-boundary.sh
Files
SKILL.mdcore6,965 bytesSKILL.mdcore6,965 bytesscripts/selftest/run-selftest.shruns154 bytesscripts/selftest/verify-review-boundary.shruns920 bytes
Read SKILL.md
# Owner Intent Audit
The question this review answers is not "is the artifact good" but **"is this what the owner
meant, and what did the agent leave behind while making it?"** (The owner is whoever owns the
work and decides what it should be; often that is the user.) An agent can produce a PRD (product
requirements document), a plan, or a diff that is locally excellent and still specify a different product, carry work
nobody asked for, or hide the debts agents characteristically create. Reviewing the artifact
for its own defects — bugs, security holes, silent death — is peer-review's job, not this one;
the two are run separately and neither substitutes for the other.
- **Plan mode:** PRDs, designs, specs, task lists, refactor plans, and test plans.
- **Code mode:** diffs, files, tests, or subsystems substantially written by agents.
Start with the ordinary user and system flow. Realistic common-path failure outranks exoticpeer-review
When your agent uses it
Adversarial review and fix loop for code, specs, plans, and migration manifests.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
7,693 tokensWhen the skill is activated
Reference documents
13,923 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Review Calibration
- Routing rules — read first
- Phase 0: Classify
- Phase 1: Context & Review
- Phase 2: Fix (code) or Report (docs)
- Phase 3: Re-review loop (code only) — HARD-CAPPED
- Phase 4: Final report
- Safety
- Usage examples
Scripts executed separately
scripts/lib/sno-model.shscripts/review-backfill.shscripts/review-findings.shscripts/review-receipt.shscripts/run-adversarial-review.shscripts/selftest/cursor-process-group.tscripts/selftest/run-cross-vendor.shscripts/selftest/run-model-settings.shscripts/selftest/run-selftest.sh
Files
SKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesSKILL.mdcore33,452 bytesagents/openai.yamlasset216 bytesassets/adversarial-plan-review.prompt.mddoc11,315 bytesassets/adversarial-review.prompt.mddoc12,249 bytesassets/adversarial-test-review.prompt.mddoc3,617 bytesreferences/code-layers.mddoc5,490 bytesreferences/doc-layers.mddoc5,598 bytesreferences/python-advanced-patterns.mddoc7,962 bytesreferences/python-standards.mddoc8,517 bytesreferences/ts-standards.mddoc7,299 bytesscripts/lib/sno-model.shruns1,490 bytesscripts/review-backfill.shruns4,716 bytesscripts/review-findings.shruns11,967 bytesscripts/review-receipt.shruns5,384 bytesscripts/run-adversarial-review.shruns58,475 bytesscripts/selftest/cursor-process-group.truns2,094 bytesscripts/selftest/run-cross-vendor.shruns14,842 bytesscripts/selftest/run-model-settings.shruns5,179 bytesscripts/selftest/run-selftest.shruns38,745 bytes
Read SKILL.md
# Peer Review
Classify → gather context → **run bundled adversarial-review script** → root cause → fix/report → repeat until clean.
"Owner" below means whoever owns the work, usually the user.
Prerequisites: Linux, bash, python3, jq, GNU `date`, `timeout`, `sha1sum`, `pgrep` and GNU `xargs`, Sno's quota pick and answer-provider commands, plus an installed, logged-in reviewer CLI on another vendor. Without python3 the findings ledger and receipts do not work.
The bundled script's adversarial-review pass is the authoritative reviewer. It runs in a fresh, separate headless session that has none of the caller's conversation. Only an answer from a different model vendor counts: the script walks Sno's ordered reviewer candidates and discards failed, empty, unknown-vendor or same-vendor answers. There is no same-vendor fallback. The active agent gathers context, investigates root causes, and applies fixes — it never overrides, filters, softens, or rewords the nested reviewer's findings. Every authoritative finding reaches the user; tag suspected false positives `[Possible FP]` with your reasoning instead of dropping them. Findings the active agent adds on its own are labeled "Active-agent supplementary" and kept clearly separate.
Works for both code and documents: classify first, then load the right verification layers. Code gets a root-cause-driven fix loop; documents get a structured report with optional edits.
## Review Calibration
test-writer
When your agent uses it
Write and improve test-owned code: tests, test scripts, fixtures, evals, and test-only helpers. Use whenever Codex is asked to create or change test code. Its only job is to produce the strongest practical tests in the repository's existing harness, run them, and fix defects in the test code.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,173 tokensWhen the skill is activated
Reference documents
1,993 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Test scope
- Single responsibility
- Core principles
- Test ownership
- Write the code
- Test quality
- Optional code references
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,717 bytesreferences/eval-sim-patterns.mddoc8,688 bytesscripts/selftest/run-selftest.shruns874 bytes
Read SKILL.md
# Test Writer
Write the best test code for the requested behavior. Start with the repository and the
behavior.
## Test scope
- Run tests only for the changed behavior and its directly affected callers or integrations.
- Do not run full evaluation, unit, integration, repository, site, or all-module suites unless the owner explicitly requests them.
- A skill, PRD, reviewer, repository document, or default package script does not grant that permission.
- After a failure, rerun the failing case first. Once it passes, run only directly affected cases; do not expand by default.
- Build artifacts required for a requested deployment are not permission to run unrelated tests.
- Every development task has a finite budget including setup, execution, and reporting; before each run, estimate duration from available timings and name the changed behavior it verifies, using a stated estimate when timings are unknown rather than building a timing system or running a preliminary suite.
- Remove checks and repeated runs that neither establish the requested main function nor expose its defects; select the smallest useful test that fits the remaining development budget, never spend it on reassurance.codex-coder
When your agent uses it
Route production coding tasks from Claude Code to the user-level Codex Shell, TypeScript, Python, or Rust workflow through a direct `codex exec` run. Use for "codex-coder", "ask Codex to write code", "generate with Codex", language migrations, or mixed Shell/TypeScript/Python/Rust implementation.
What it loads into context
Frontmatter
167 tokensAlways available to the agent
SKILL.md
2,407 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
- Codex runs with the sandbox off
- Transport: `codex exec` from the dispatching session
- Route the Target Language
- Build One Codex Handoff
- Launch and wait
- Failure Boundary
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore10,537 bytesSKILL.mdcore10,537 bytesSKILL.mdcore10,537 bytesSKILL.mdcore10,537 bytesSKILL.mdcore10,537 bytesscripts/selftest/run-selftest.shruns212 bytesscripts/selftest/text-check.pyruns1,744 bytes
Read SKILL.md
# Codex Coder Router for Claude Code
Carry the task's finite time budget into the coding assignment, including test time.
Require a duration estimate before each targeted test run; full evaluation, unit,
integration, or repository suites require the owner's explicit request, not dispatcher
approval. New security checks require the owner's specific approval; auxiliary checks
must not block the requested function or development work.
Act as a thin dispatcher. Determine the target language, then hand the whole implementation to Codex through a direct `codex exec` run owned by this session. The canonical language instructions live under `~/.codex/skills`; do not use same-named Claude skills as substitutes.
Dispatch always uses `low` effort, set by this skill's frontmatter. The separate Codex coding task uses the model from role `coder` with `high` effort. If the original request selects the reviewer model, use the model from role `reviewer` with `low` effort. Roles live in the `[models]` table of `${XDG_CONFIG_HOME:-$HOME/.config}/sno/models.toml`; an absent file, missing role, or empty value means omit `--model` so the Codex default applies. An effort explicitly selected in the original request overrides either default. Loading a language skill does not switch effort inside a running task: set both values when launching that task.
## Codex runs with the sandbox off
codex-coder
When your agent uses it
Route production coding tasks to the user-level Shell, TypeScript, Python, or Rust Codex workflow. Use for "codex-coder", "Codex write", "generate with Codex", language migrations, or mixed Shell/TypeScript/Python/Rust implementation when Codex should choose the correct language specialist automatically.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
1,038 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
- Codex runs with the sandbox off
- Route the Target Language
- Load the Canonical Skill
- Mixed-Language Work
- Failure Boundary
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore4,880 bytesSKILL.mdcore4,880 bytesSKILL.mdcore4,880 bytesscripts/selftest/run-selftest.shruns212 bytesscripts/selftest/text-check.pyruns1,450 bytes
Read SKILL.md
# Codex Coder Router
Carry the task's finite time budget into the coding assignment, including test time.
Require a duration estimate before each targeted test run; full evaluation, unit,
integration, or repository suites require the owner's explicit request, not dispatcher
approval. New security checks require the owner's specific approval; auxiliary checks
must not block the requested function or development work.
Act as a thin dispatcher. Select the language skill, then let that skill own repository discovery, prompting, implementation, verification, and refinement. Do not keep a second copy of language rules here.
## Codex runs with the sandbox off
Keep the owner's configured `sandbox_mode = "danger-full-access"`; do not override it
in a dispatch, config, flag, or profile. A connection or credential error does not identifymedic
When your agent uses it
Check that this machine's agent team can work and say what is wrong in plain lines: tools installed, core skills installed, skill commands runnable, hooks configured, Reach seat live, a heartbeat running, both vendors' quota readable, temp space free. Checks only, never repairs. Use on a new machine, when agents stop reaching each other or a long run fails to start, or when the owner asks whether everything is healthy.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
993 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
- Use
- What each check reads
- Limits
Scripts executed separately
scripts/medicscripts/medic.tscripts/selftest/run-selftest.sh
Files
SKILL.mdcore3,787 bytesSKILL.mdcore3,787 bytesscripts/medicruns9,439 bytesscripts/medic.truns10,543 bytesscripts/selftest/run-selftest.shruns1,369 bytes
Read SKILL.md
# medic
`sno medic run` looks at the agent team on this machine and prints one line per check. It reads and
reports; it never installs, repairs, starts, stops or spends anything.
```
OK <check>: <what was found>
WARN <check>: <what is wrong> -> <the command that fixes it>
FAIL <check>: <what is wrong> -> <the command that fixes it>
MEDIC ok=N warn=N fail=N
```
`FAIL` means the team cannot work at all (a required program is missing, no agent command line is
installed, Reach is broken). `WARN` means it works worse than it should. Exit status is 0 when there ispython-coder
When your agent uses it
Implement and refactor production Python, FastAPI, Pydantic, async, and migrations.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,601 tokensWhen the skill is activated
Reference documents
2,043 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Runtime Source of Truth
- Boundaries
- Design Rules
- Verification
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore7,427 bytesSKILL.mdcore7,427 bytesreferences/advanced-patterns.mddoc8,777 bytesscripts/selftest/run-selftest.shruns1,277 bytes
Read SKILL.md
# Python Coder
Every development task has a finite budget including setup, tests, and reporting.
Before running tests, estimate duration from available timings and identify the changed
behavior or directly affected consumer. If timing is unknown, state an estimate; do not
build a timing system or run a preliminary suite. Full evaluation, unit, integration,
or repository suites require the owner's explicit request, never a skill, PRD, review,
or default command. Remove checks that neither prove the requested main function nor
expose its defects. Repeat only after a relevant change or failure.
Every new security check requires the owner's explicit approval for that specific check;
remove auxiliary security, assertion, hash, or bookkeeping blockers of useful work.
Write production Python that fits the current repository, stays small, and is easy to verify. Local repo instructions add project-specific detail; they do not weaken these rules.rust-coder
When your agent uses it
Implement, refactor, and migrate production Rust with repository-grounded ownership, type-driven invariants, explicit errors, safe concurrency, minimal unsafe code, and verified Cargo workflows. Use for Rust features, crates, CLIs, services, libraries, async code, FFI, performance work, migrations, or substantial .rs and Cargo.toml changes, including requests such as 'rust-coder', 'write Rust', or 'implement this Rust feature with Codex'.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
795 tokensWhen the skill is activated
Reference documents
3,512 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inspect
- Design and implement
- Verify
- Report
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore3,875 bytesagents/openai.yamlasset236 bytesreferences/standards.mddoc17,490 bytesscripts/selftest/run-selftest.shruns1,355 bytes
Read SKILL.md
# Rust Coder
Implement directly in the current Codex session. Do not launch another Codex process.
Read [references/standards.md](references/standards.md) completely before editing. Repository instructions and the declared toolchain override generic preferences.
## Inspect
Read the smallest complete set of evidence:
- Nearest `AGENTS.md`, `CLAUDE.md`, and repository instructions.
- Root and target `Cargo.toml`, `Cargo.lock`, `rust-toolchain*`, Cargo configuration, lint and format configuration, features, targets, and continuous-integration commands.
- Every target file in full, its parent exports, immediate callers, traits, types, errors, feature gates, platform boundaries, focused tests, and one or two tested sibling modules.
- The exact format, check, test, Clippy, feature, and target commands used by the crate.shellscript-coder
When your agent uses it
Implement and refactor production shell scripts, command-line tools, automation, process wrappers, and Git or infrastructure helpers with reliable failures, useful logs, and machine-readable output.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,494 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
- Read Before Writing
- Boundaries
- Reliability
- Messages and Agent-Facing Interfaces
- Failure Design
- Verification
- Delivery
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore7,617 bytesscripts/selftest/run-selftest.shruns1,326 bytes
Read SKILL.md
# Shell Script Coder
Every development task has a finite budget including setup, tests, and reporting.
Before running tests, estimate duration from available timings and identify the changed
behavior or directly affected consumer. If timing is unknown, state an estimate; do not
build a timing system or run a preliminary suite. Full evaluation, unit, integration,
or repository suites require the owner's explicit request, never a skill, PRD, review,
or default command. Remove checks that neither prove the requested main function nor
expose its defects. Repeat only after a relevant change or failure.
Every new security check requires the owner's explicit approval for that specific check;
remove auxiliary security, assertion, hash, or bookkeeping blockers of useful work.
Write small, production-grade Bash that fits the repository and remains understandable during failure. Local instructions define the runtime and style; they may strengthen these rules but not weaken reliability.sno-cli
When your agent uses it
Operate the `sno` command-line tool: install, update, check, and uninstall Sno products, read the exact commands and flags of the installed version, and run the account, skills, onboarding, Station telemetry and REM commands. Use when the owner or a task says "sno", "Sno CLI", "sno setup", "sno update", "sno doctor", "sno uninstall", "sno station", "telemetry consent", "rem verdict", "sno account", or "sno skills". The exact flags always come from the installed binary, never from this file. Do not use it to decide the owner's choices for them.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
1,901 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
- Start Here
- Conventions
- Sno GPU attribution
- Task map
- Recipes
- Owner-only actions
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore7,705 bytesSKILL.mdcore7,705 bytesscripts/selftest/run-selftest.shruns297 bytesscripts/selftest/text-check.pyruns4,034 bytes
Read SKILL.md
# Sno CLI
`sno` is one binary. This file carries the rules, the task map and the recipes. The exact
commands and flags of the version that is installed are served by the binary itself, so they
cannot be out of date.
## Start Here
Choose the executable once and keep using it:
- Use the absolute path the installer printed.
- Otherwise run `type -a sno` (works in bash and zsh). If two `sno` files are listed, or the version is older
than the installer said, tell the owner, use the newer absolute path, and note that a
running shell may need `hash -r` or a new terminal.ts-coder
When your agent uses it
Implement and refactor production TypeScript/TSX, strict types, APIs, and migrations.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,083 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
- Boundaries
- Standards
- Migrations
- Verification
- Delivery
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,545 bytesSKILL.mdcore5,545 bytesscripts/selftest/run-selftest.shruns1,201 bytes
Read SKILL.md
# TypeScript Coder
Every development task has a finite budget including setup, tests, and reporting.
Before running tests, estimate duration from available timings and identify the changed
behavior or directly affected consumer. If timing is unknown, state an estimate; do not
build a timing system or run a preliminary suite. Full evaluation, unit, integration,
or repository suites require the owner's explicit request, never a skill, PRD, review,
or default command. Remove checks that neither prove the requested main function nor
expose its defects. Repeat only after a relevant change or failure.
Every new security check requires the owner's explicit approval for that specific check;
remove auxiliary security, assertion, hash, or bookkeeping blockers of useful work.
Write TypeScript that fits the current repository, stays small, and is easy to verify. Local repo instructions add project-specific detail; they do not weaken these rules.rem-reflect
When your agent uses it
Self Learning from this machine's Claude Code, Codex, Hermes, OpenClaw and Cursor sessions. Decide skill changes and lessons with accept/reject/tbd; recall lessons at session start.
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
3,378 tokensWhen the skill is activated
Reference documents
249 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Sno GPU attribution
- Commands
- How proposals are classified
- Owner actions
Scripts executed separately
scripts/adopt.test.tsscripts/adopt.tsscripts/agent-sessions.tsscripts/allowance-fallback.test.tsscripts/allowance-request-isolation.test.tsscripts/backend.tsscripts/calls.tsscripts/catalogue-cloud.test.tsscripts/catalogue.tsscripts/chunk.tsscripts/cloud-apply.test.tsscripts/cloud-batch.test.tsscripts/cloud-day.test.tsscripts/cloud-verdict.test.tsscripts/cloud-wait.test.tsscripts/cloud.tsscripts/config.tsscripts/cursor.test.tsscripts/cursor.tsscripts/evidence.tsscripts/first-message.test.tsscripts/harvest.test.tsscripts/harvest.tsscripts/hermes-openclaw.test.tsscripts/identity.test.tsscripts/identity.tsscripts/installed-roots.test.tsscripts/journey-adopt-lesson.test.tsscripts/journey-ops.test.tsscripts/labeler.test.tsscripts/labeler.tsscripts/ledger.tsscripts/lessons.tsscripts/local-filter.test.tsscripts/local-first-output.test.tsscripts/local-settings.tsscripts/local-writer.tsscripts/login-in-place.test.tsscripts/model-json.tsscripts/no-network.test.tsscripts/observe.tsscripts/page-journey.test.tsscripts/pages.test.tsscripts/pages.tsscripts/proposer-loop.test.tsscripts/proposer-validate.test.tsscripts/proposer.tsscripts/recall-hook.test.tsscripts/recall.test.tsscripts/recall.tsscripts/reflect.test.tsscripts/reflect.tsscripts/rem-reflectscripts/rem-reflect.tsscripts/render-chunk.test.tsscripts/render.tsscripts/report.tsscripts/run-status.test.tsscripts/sampling.test.tsscripts/sampling.tsscripts/selftest-guard.test.tsscripts/selftest/bin/claudescripts/selftest/bin/codexscripts/selftest/bin/shim-core.cjsscripts/selftest/bin/snoscripts/selftest/journey-e2e.shscripts/selftest/journey.mjsscripts/selftest/observe-journey.mjsscripts/selftest/run-selftest.shscripts/selftest/spawn-python.mjsscripts/session.test.tsscripts/session.tsscripts/signal-local.test.tsscripts/skill-impact.test.tsscripts/station-settings.test.tsscripts/store-memory.test.tsscripts/store.tsscripts/test-helpers.tsscripts/text.tsscripts/trigger.test.tsscripts/trigger.tsscripts/verdicts.test.tsscripts/verdicts.ts
Files
SKILL.mdcore14,407 bytesreferences/labeler.mddoc1,216 bytesreferences/labeler.schema.jsonasset1,710 bytesreferences/local-settings.jsonasset126 bytesreferences/local-writer.schema.jsonasset2,400 bytesreferences/proposal.schema.jsonasset3,265 bytesreferences/render.jsonasset245 bytesreferences/signals.jsonasset71 bytesreferences/text.jsonasset4,106 bytesscripts/adopt.test.tsruns13,355 bytesscripts/adopt.tsruns14,657 bytesscripts/agent-sessions.tsruns9,268 bytesscripts/allowance-fallback.test.tsruns16,340 bytesscripts/allowance-request-isolation.test.tsruns7,301 bytesscripts/backend.tsruns9,338 bytesscripts/calls.tsruns8,800 bytesscripts/catalogue-cloud.test.tsruns1,485 bytesscripts/catalogue.tsruns3,299 bytesscripts/chunk.tsruns2,126 bytesscripts/cloud-apply.test.tsruns25,825 bytesscripts/cloud-batch.test.tsruns11,423 bytesscripts/cloud-day.test.tsruns7,002 bytesscripts/cloud-verdict.test.tsruns12,410 bytesscripts/cloud-wait.test.tsruns1,348 bytesscripts/cloud.tsruns25,002 bytesscripts/config.tsruns8,293 bytesscripts/cursor.test.tsruns16,108 bytesscripts/cursor.tsruns6,898 bytesscripts/evidence.tsruns1,583 bytesscripts/first-message.test.tsruns10,531 bytesscripts/harvest.test.tsruns16,885 bytesscripts/harvest.tsruns23,157 bytesscripts/hermes-openclaw.test.tsruns26,179 bytesscripts/identity.test.tsruns3,336 bytesscripts/identity.tsruns3,571 bytesscripts/installed-roots.test.tsruns11,277 bytesscripts/journey-adopt-lesson.test.tsruns4,242 bytesscripts/journey-ops.test.tsruns7,655 bytesscripts/labeler.test.tsruns3,644 bytesscripts/labeler.tsruns9,764 bytesscripts/ledger.tsruns2,200 bytesscripts/lessons.tsruns4,797 bytesscripts/local-filter.test.tsruns3,995 bytesscripts/local-first-output.test.tsruns22,598 bytesscripts/local-settings.tsruns1,457 bytesscripts/local-writer.tsruns12,903 bytesscripts/login-in-place.test.tsruns5,944 bytesscripts/model-json.tsruns4,209 bytesscripts/no-network.test.tsruns5,162 bytesscripts/observe.tsruns1,466 bytesscripts/page-journey.test.tsruns6,810 bytesscripts/pages.test.tsruns4,243 bytesscripts/pages.tsruns4,894 bytesscripts/proposer-loop.test.tsruns1,503 bytesscripts/proposer-validate.test.tsruns9,355 bytesscripts/proposer.tsruns8,864 bytesscripts/recall-hook.test.tsruns21,376 bytesscripts/recall.test.tsruns32,149 bytesscripts/recall.tsruns18,613 bytesscripts/reflect.test.tsruns9,472 bytesscripts/reflect.tsruns14,624 bytesscripts/rem-reflectruns823 bytesscripts/rem-reflect.tsruns18,198 bytesscripts/render-chunk.test.tsruns7,353 bytesscripts/render.tsruns9,890 bytesscripts/report.tsruns8,380 bytesscripts/run-status.test.tsruns19,586 bytesscripts/sampling.test.tsruns2,164 bytesscripts/sampling.tsruns915 bytesscripts/selftest-guard.test.tsruns4,089 bytesscripts/selftest/bin/clauderuns94 bytesscripts/selftest/bin/codexruns93 bytesscripts/selftest/bin/shim-core.cjsruns4,705 bytesscripts/selftest/bin/snoruns5,818 bytesscripts/selftest/fixtures/hermes-session-export.jsonlasset1,498 bytesscripts/selftest/fixtures/openclaw-events.jsonlasset3,793 bytesscripts/selftest/fixtures/verdict-traces.jsonasset16,989 bytesscripts/selftest/journey-e2e.shruns1,384 bytesscripts/selftest/journey.mjsruns9,740 bytesscripts/selftest/observe-journey.mjsruns12,800 bytesscripts/selftest/run-selftest.shruns6,770 bytesscripts/selftest/spawn-python.mjsruns765 bytesscripts/session.test.tsruns5,251 bytesscripts/session.tsruns251 bytesscripts/signal-local.test.tsruns7,207 bytesscripts/skill-impact.test.tsruns6,313 bytesscripts/station-settings.test.tsruns13,977 bytesscripts/store-memory.test.tsruns3,522 bytesscripts/store.tsruns7,917 bytesscripts/test-helpers.tsruns15,672 bytesscripts/text.tsruns760 bytesscripts/trigger.test.tsruns3,726 bytesscripts/trigger.tsruns2,587 bytesscripts/verdicts.test.tsruns8,284 bytesscripts/verdicts.tsruns8,179 bytes
Read SKILL.md
# Self Learning
> **Before you use it.** Sno Station sets the sharing level when it installs, by mode: `full` for `agent-native` and
> `rem-enhanced`, `metadata-only` for `local-first`; it never overwrites a choice you already made. At `full`, this tool sends
> the text of your Claude Code, Codex, Hermes, OpenClaw and Cursor sessions and every installed skill to Sno's cloud. It uses your
> Claude and Codex login in place and copies only Cursor's login into its isolated home to label sessions. In `local-first` nothing is sent to Sno, but the
> text of a few sessions a night still goes to each session's own agent account when this tool asks it for lessons; Hermes and OpenClaw use their own login without a credential copy.
> "What a run reads, copies and uploads" below lists everything.
> Turn uploading off at any time with `sno station consent off`.
Self Learning (`rem-reflect`) reads this machine's Claude Code, Codex, Hermes, OpenClaw and Cursor sessions once a day. When the Sno Station
settings select `agent-native` or `rem-enhanced`, each session's own CLI (on the
host's default model) conservatively decides keep/drop and labels its outcome. Each completed run
is sent through `sno rem judge`; that command permits session and skill uploads only at full consent.handoff
When your agent uses it
Transfer full task ownership to a fresh agent with a verified brief and explicit release. Use for replacing the current executor, including a directly assigned task with no work card; not for supervising a helper.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
4,244 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
- Three entry shapes
- Procedure
- Progress record
- When the sender is gone
- Failure and retry
- Short launcher
- Release message
Scripts executed separately
scripts/handoff-checkpointscripts/handoff-checkpoint.tscripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore18,773 bytesSKILL.mdcore18,773 bytesreferences/reach-contract.jsonasset1,431 bytesscripts/handoff-checkpointruns9,557 bytesscripts/handoff-checkpoint.truns8,140 bytesscripts/selftest/run-selftest.shruns167 bytesscripts/selftest/text-check.pyruns12,968 bytes
Read SKILL.md
# Handoff
Transfer the owner's task, current state and existing authority to one receiving agent.
The owner is whoever owns the work, usually the user.
**The receiver does not edit until explicit release.** After verified release the sender stops execution; it does not supervise or wait for completion.
Use the installed Reach guide and `sno reach --help` for exact card syntax and command
arguments. [The bundled contract](references/reach-contract.json) bounds the text self-test;
it does not prove an installed runtime. Confirm `sno reach --version` and the required
runtime before creating a receiver. If unavailable, retain ownership and report the missing
input. No runtime or installation is bundled with this skill.
Install/update through `sno setup`; install any named missing prerequisite before transferring ownership.
On macOS use the corresponding Homebrew formula: `bash`, `coreutils`, `findutils`,heartbeat
When your agent uses it
Set recurring checks or completion watches with `sno heartbeat` and its persistent log reader. Use for periodic reports or unattended long runs. Not for calendar scheduling or commands watched directly.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
3,122 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
- 1. Report every so often
- 2. Wait until something is done
- The one rule
- What every ending tells you
- Flags
- Starting and stopping
- Many agents at once
- Reading the log
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore12,327 bytesreferences/heartbeat-contract.jsonasset363 bytesscripts/selftest/run-selftest.shruns204 bytesscripts/selftest/text-check.pyruns4,910 bytes
Read SKILL.md
# heartbeat
Use the `sno heartbeat` command installed by `sno setup`. This skill supplies
instructions, not a program copy. If the command names a missing prerequisite, install
that tool and retry. On macOS install Homebrew `coreutils` (GNU `timeout`, `tail` and `mv`) and
put its `libexec/gnubin` directory on PATH; newer versions of the command also find the
`g`-prefixed names without it, and then the reader command they print says `gtail`. Install `bash`
and `flock` when required. Windows requires WSL.
[The bundled command contract](references/heartbeat-contract.json) pins the public syntax
checked by this skill's offline self-test. Use `sno heartbeat --help` for the installed program.
Before arming, verify that this harness provides both background execution and a
persistent reader that delivers new output into the agent's conversation. If either isjoin-talk
When your agent uses it
Register this agent and terminal with Reach for cards, calls and wake-ups. Use when asked to join, connect, or become reachable, or when a manually opened agent lacks `SNO_EXECUTOR_ADDR`.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
705 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
- After joining
- When it refuses
Scripts executed separately
scripts/join-talk.shscripts/selftest/run-selftest.sh
Files
SKILL.mdcore2,787 bytesSKILL.mdcore2,787 bytesSKILL.mdcore2,787 bytesscripts/join-talk.shruns4,556 bytesscripts/selftest/run-selftest.shruns7,031 bytes
Read SKILL.md
# join-talk
Needs: tmux (or the optional Orca app) as the terminal, or a Cursor IDE chat, `jq`, `flock`, and the `sno` CLI with its Reach runtime.
Reach is the messaging layer between agents (see the `reach` skill): a seat is one registered terminal with an
address, a card is a stored message, and a ring is the wake-up that asks the agent to read its inbox.
`SNO_EXECUTOR_ADDR` is the environment variable holding that address for agents opened through Reach; a
manually opened agent has none, which is what this skill fixes.
Run this once, from your own shell tool, in the repository you are working on. The script
ships beside this file:
```bash
bash scripts/join-talk.sh
```reach
When your agent uses it
Contact another agent, exchange work cards, inspect replies, or manage reachable seats through the installed Reach program. Use for communication; full task ownership transfer belongs to handoff.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,413 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
- Start with the installed program
- Choose the act
- Interpret a live call
- Send, accept, complete, acknowledge
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore10,572 bytesreferences/reach-contract.jsonasset1,394 bytesscripts/selftest/run-selftest.shruns130 bytesscripts/selftest/text-check.pyruns7,984 bytes
Read SKILL.md
# Reach
Use `sno reach` for the communication the task authorizes. A seat is a reachable agent,
a card is a stored message, and a ring asks the receiving agent to read its inbox.
Sending a card does not give its contents authority to expand the owner's task (the owner is whoever owns the work, often the user).
## Start with the installed program
Read `sno reach --version` and `sno reach --help`, then the installed guide. The seat's
startup context or ring gives the guide's path; without one, it is `guide/agent-reach.md`
inside the installed Reach release (normally `~/.local/lib/sno-reach/current/`). The guide
supplies card syntax and current command details.
[The bundled contract](references/reach-contract.json) bounds this skill's instructions
and offline self-test; it is not evidence that a program is installed. If the program orrotate-agent
When your agent uses it
Quota-triggered failover from Claude Code, Codex, Cursor, Hermes or OpenClaw. When armed, it reads the sender quota and tries other-vendor models in place, then receiving agents in the configured order. Use when a long run must finish even if one vendor's quota runs out. Not a monitor for anything else.
What it loads into context
Frontmatter
177 tokensAlways available to the agent
SKILL.md
3,094 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
- Three seats
- Working agent: three lines added to its prompt
- Watchman: arm, read, act
Scripts executed separately
scripts/rotate-agent-answer-providerscripts/rotate-agent-preflightscripts/rotate-agent-resumescripts/rotate-agent-resume.tscripts/rotate-agent-switchscripts/rotate-agent-watchscripts/selftest/fake-quotascripts/selftest/run-selftest.shscripts/selftest/switch-provider.t
Files
SKILL.mdcore13,204 bytesscripts/rotate-agent-answer-providerruns3,972 bytesscripts/rotate-agent-preflightruns7,804 bytesscripts/rotate-agent-resumeruns12,955 bytesscripts/rotate-agent-resume.truns10,121 bytesscripts/rotate-agent-switchruns5,242 bytesscripts/rotate-agent-watchruns6,767 bytesscripts/selftest/fake-quotaruns267 bytesscripts/selftest/run-selftest.shruns9,366 bytesscripts/selftest/switch-provider.truns16,035 bytes
Read SKILL.md
# rotate-agent
Needs: `tmux`, `jq`, GNU `timeout`, and `sno` with Reach, heartbeat and
subscription-quota-check, plus the `handoff` skill. The provider-reading script also
uses `awk` and OpenClaw's session exporter. Install programs through `sno setup`.
A seat is a registered terminal address (see `join-talk`). The owner owns the work;
the watchman reads ticks and acts on them, preferably from a seat other than the busy sender.
Rotation keeps one authorized long run working when its model's quota is low.
Agent ids are `claude-code`, `codex`, `cursor`, `hermes`, `openclaw`. Selection belongs
to `sno subscription-quota-check --pick handoff`: other-vendor models inside the sender
first, then other agents in `handoff_order`. Never replace the returned order with your own.
A Cursor quota reading belongs to one conversation, so `--from cursor` needs
`--sender <A-seat>` on the preflight and `--seat <A-seat>` on the watch; without itsubscription-quota-check
When your agent uses it
Read remaining Claude Code and Codex subscription quota without spending it. Use when the user asks or after a vendor rejects work for quota; a caller such as rotate-agent may also arm a scheduled read on purpose. Never poll on your own; after a `wait` verdict, pass the reset wait to `sno heartbeat` and re-read once when it ends.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
1,977 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
- Running it
- What comes back
- When it says wait
- Five things that stay true
- Version fragility, stated plainly
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore8,377 bytesSKILL.mdcore8,377 bytesreferences/heartbeat-contract.jsonasset363 bytesreferences/subscription-quota-check-contract.jsonasset342 bytesscripts/selftest/run-selftest.shruns204 bytesscripts/selftest/text-check.pyruns6,400 bytes
Read SKILL.md
# subscription-quota-check
## The one rule
**Read it on demand: when the human asks, or when something was actually blocked.**
This skill is not a monitor and never schedules a read of its own, apart from the single re-confirmation read after a `wait` verdict (see "When it says wait"). The Claude usage endpoint
is itself rate limited, so a probe on a timer eventually earns a 429 and starts serving
cached numbers — a checker that reports confidently while reading nothing. A caller such as
rotate-agent may arm a scheduled read deliberately; that is the caller's decision, and the
rate-limit risk is then the caller's to manage. Outside such an armed schedule, every run
must trace to one of the two moments above.
The anti-pattern it replaces has a name: **finding out you are out of quota by making a realcharter
When your agent uses it
Write, revise or review a charter: the one document that tells an executor what to deliver, what is out of bounds, what the owner already decided, and how each success check will be proven. Use when work needs a written brief before someone else does it, or when asked to write, change or check a charter.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,074 tokensWhen the skill is activated
Reference documents
766 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Rules that keep a charter useful
- Write
- Revise
- Review only
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesSKILL.mdcore4,835 bytesreferences/questions.mddoc847 bytesreferences/template.mddoc2,447 bytesscripts/selftest/run-selftest.shruns1,561 bytes
Read SKILL.md
# charter
A charter is one markdown file that says what to deliver and how everyone will know it was
delivered. A task is named by its charter
filename. `charter` writes it; `deliver` carries a released charter out. Any kind of project
uses it: software, documents, campaigns, research, operations. The owner is whoever owns the
work (often the user); speak to them in the language they use.
Prerequisites: none to use it; its selftest needs bash and python3.
Read `references/template.md` for the file layout and `references/questions.md` before asking
the owner anything.
## Rules that keep a charter usefulcos
When your agent uses it
MANUAL-ONLY: load solely when the human owner types `/cos`, uses `$cos`, or asks you to act as the Chief of Staff (COS). The COS is the one agent the owner talks to; it coordinates the owner and the per-project Project Leads (PLs). A task card, charter, or dispatch makes you an executor, not COS.
What it loads into context
Frontmatter
242 tokensAlways available to the agent
SKILL.md
18,440 tokensWhen the skill is activated
Reference documents
6,923 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Development scope, time, and owner approval
- LAWS — bare, binding, in load order
- Decision discipline — when to act, what may settle it, when to stop
- Where COS may overrule a PL
- The charter-filename law
- Prerequisites and terms
- Fast thinking, slow thinking — the switch
- Sub-skill routing — explicit invocation, never guesswork
- PART 2 — procedures and mechanics
- Scope is a roster, never a repository
- The mail law — the one that matters most
- Card timing — free before launch, expensive after
- Acting on the six reasons — procedures
- Talking to the owner
- Repairing a board — bounded, sourced, and never satisfied by an empty section
- Promised is not started — the same law as sent-is-not-received, one layer up
- Interrogate your own instruments — the scepticism you apply downward, applied inward
- Owner-designated evaluations
- Boot ritual — every session start, and every restart
- Liveness — the turn lock first, the heartbeat never
- State files and canonical assets
- Boundaries
Scripts executed separately
scripts/cos-claim.shscripts/cos-claim.tscripts/cos-roster.shscripts/cos-roster.tscripts/cos-screen.shscripts/cos-screen.tscripts/cos-since.shscripts/exec-sentinel.shscripts/exec-sentinel.tscripts/exec-tree-check.shscripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
LEARNING.mddoc6,232 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesSKILL.mdcore77,869 bytesreferences/card-template.mddoc11,124 bytesreferences/digest-template.mddoc4,986 bytesreferences/owner-profile.mddoc5,426 bytesreferences/pocket-card.mddoc1,590 bytesscripts/cos-claim.shruns30,176 bytesscripts/cos-claim.truns12,698 bytesscripts/cos-roster.shruns41,501 bytesscripts/cos-roster.truns7,157 bytesscripts/cos-screen.shruns4,902 bytesscripts/cos-screen.truns2,546 bytesscripts/cos-since.shruns3,703 bytesscripts/exec-sentinel.shruns6,157 bytesscripts/exec-sentinel.truns2,479 bytesscripts/exec-tree-check.shruns2,687 bytesscripts/selftest/run-selftest.shruns204 bytesscripts/selftest/text-check.pyruns1,036 bytes
Read SKILL.md
# COS — Chief of Staff (the layer above the PLs)
## Development scope, time, and owner approval
"Owner" means whoever owns the work, usually the user.
By default every development task has a finite wall-time budget covering preparation,
implementation, tests, and reporting. Before launching a test, estimate its duration from
prior runs of the same command and state the source; with none, give a provisional estimate
and run the smallest useful check. Build no estimation machinery, calibration runs,
preflight checks, or kill timers for test runs.
Test only the changed behavior and its direct consumers. By default do not run a full
evaluation, unit, integration, end-to-end, or repository suite, and do not add a securitycos-evolve
When your agent uses it
Turn repeated management failures into enforced COS or PL rules. Load ONLY after the owner has explicitly activated the cos role for this session and the COS core routes here. Never invoke directly.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
3,639 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 pen's boundary — how, never what
- Step 1 — is this even a lesson?
- Step 2 — the "where" ruling
- Step 3 — a judgment lapse is mechanized, not exhorted
- Step 4 — the promotion ladder
- Step 5 — route to the right shelf
- Step 6 — is the prescription a class?
- Writing to `LEARNING.md`
- The read hooks — storage is not reading
- Mirroring — every change, verified
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore15,514 bytesSKILL.mdcore15,514 bytesscripts/selftest/run-selftest.shruns204 bytesscripts/selftest/text-check.pyruns1,059 bytes
Read SKILL.md
# COS — harvesting friction into law
Before running these commands, set `PL_SKILL_DIR` to the absolute directory of the installed `pl` skill, in the same Bash call.
Load only when the owner has explicitly activated the COS role for this session and the
COS core routes a repeated management failure here.
**Exclusive authority of this overlay: the pen over skill files and `LEARNING.md`** (the
batch review only appends the decision-rights lines named in its Pass 1). No other part of
the COS tree, and no PL, may edit them. PLs propose by card.
**The decision-rights file is different.** `~/.config/sno/decision-rights.md` is the owner's.
This overlay may propose a diff to its tunable parts only — the thresholds and the PL and
COS tables — from the batch review's recorded overturns and repeatedly approved queuedcos-review
When your agent uses it
Review PL self-approvals, estimates, board drift, and close quality after a declared night shift. Loaded ONLY by the cos core via its routing table; NEVER auto-load from context or invoke directly.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
2,938 tokensWhen the skill is activated
Reference documents
1,165 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why a batch review is safe at all
- Pass 1 — validity of what the PLs self-approved
- Pass 2 — close quality, against the four failure modes
- Pass 3 — estimate reconciliation
- Pass 3b — before any deletion-shaped alarm
- Pass 4 — board versus disk
- Pass 5 — the debt registry
- Assembling the return report
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore12,990 bytesSKILL.mdcore12,990 bytesSKILL.mdcore12,990 bytesSKILL.mdcore12,990 bytesSKILL.mdcore12,990 bytesscripts/selftest/run-selftest.shruns204 bytesscripts/selftest/text-check.pyruns1,215 bytes../cos/references/digest-template.mddoc4,986 bytes
Read SKILL.md
# COS — batch review
Apply the COS core's finite development budget and affected-test scope. Estimate setup,
execution, and reporting from available prior runtimes; do not add estimation machinery
or preflight. Full suites and new security checks need the owner's specific approval,
never COS approval. Missing auxiliary records do not stop functional work.
Before running these commands, set `PL_SKILL_DIR` to the absolute directory of the installed `pl` skill, in the same Bash call.
Loaded when the owner returns from a declared night shift, or after a batch of closes lands.
**Exclusive authority of this overlay:** issuing the doubt list that reaches the owner.
Nothing else in the COS tree may put a "this may be wrong" item in front of them.
cos-watch
When your agent uses it
Supervise active PLs, including wake cadence, liveness, recovery, large-run launches, and cross-journey order. Loaded ONLY by the cos core via its routing table; NEVER auto-load from context or invoke directly.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
3,028 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 wake cycle
- Liveness — the turn lock leads; the heartbeat is never decisive
- Decision rules live in the core
- Reopening a dead PL
- Big-run posture — the launch window
- Cross-journey sequencing — the judgment only COS can make
- Scheduling honesty
- Pausing the lane for an owner-designated evaluation
Scripts executed separately
scripts/selftest/run-selftest.shscripts/selftest/text-check.py
Files
SKILL.mdcore12,992 bytesSKILL.mdcore12,992 bytesSKILL.mdcore12,992 bytesscripts/selftest/run-selftest.shruns204 bytesscripts/selftest/text-check.pyruns1,073 bytes
Read SKILL.md
# COS — live supervision
Apply the COS core's finite development budget and affected-test scope. Estimate setup,
execution, and reporting from available prior runtimes; do not add estimation machinery
or preflight. Full suites and new security checks need the owner's specific approval,
never COS approval. Missing auxiliary records do not stop functional work.
Before running these commands, set `COS_SKILL_DIR` and `PL_SKILL_DIR` to the absolute directories of the installed `cos` and `pl` skills, in the same Bash call.
Prerequisites are listed in the `cos` core (§Prerequisites and terms): Linux, tmux, flock, jq, python3, pstree and pgrep, and the `pl` skill.
Loaded whenever anything is in flight: a journey running, a night shift open, a wake
tick firing, a PL gone quiet, a big run launching.
deliver
When your agent uses it
Carry out a released charter to a proven result: plan only as much as the work needs, do the work through the project's own workers, prove every success check with a recorded real run, get one independent review, and close honestly. Invoke explicitly as `$deliver <charter>` (Codex) or `/deliver <charter>` (Claude, Cursor), or the way your agent invokes a skill, or when a dispatch names you the executor of a charter.
What it loads into context
Frontmatter
137 tokensAlways available to the agent
SKILL.md
1,371 tokensWhen the skill is activated
Reference documents
373 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Keep the work useful
- Steps
Scripts executed separately
scripts/deliver-proofscripts/deliver-proof.tscripts/selftest/run-selftest.sh
Files
SKILL.mdcore5,861 bytesSKILL.mdcore5,861 bytesSKILL.mdcore5,861 bytesSKILL.mdcore5,861 bytesreferences/proof.mddoc1,806 bytesscripts/deliver-proofruns6,216 bytesscripts/deliver-proof.truns13,182 bytesscripts/selftest/run-selftest.shruns1,729 bytes
Read SKILL.md
# deliver
Carry out the named charter. Its `## Success checks` are the definition of done; nothing else
is. Read the whole charter and the existing work first. The owner (whoever owns the work,
often the user) can override this skill and any plan an agent wrote. Any kind of project uses
it: for code and tests also read `references/proof.md`.
Prerequisites: `sno deliver-proof` needs bash 4+ and GNU coreutils (Linux) and prints one message
and stops when they are missing; its selftest also needs python3. On macOS, install bash 4+ and
GNU coreutils (for example with Homebrew) and put them first on PATH. If `sno deliver-proof` is not
available, run `scripts/deliver-proof` from this skill's folder instead.
## Keep the work useful
pl
When your agent uses it
MANUAL-ONLY — load solely when the human owner types `/pl`, uses `$pl`, or asks you to act as the Project Lead (PL). Supervise one project lane and its executor agents. A charter or dispatch means: you are an EXECUTOR, not the PL.
What it loads into context
Frontmatter
259 tokensAlways available to the agent
SKILL.md
15,306 tokensWhen the skill is activated
Reference documents
13,252 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Development scope, time, and owner approval
- LAWS — bare, binding, in load order
- Decision discipline — who may rule, how a ruling is made, when to stop
- Sub-skill routing — EXPLICIT invocation, never guesswork
- Launch ladders — Iron rule 0b procedures
- Status board + context anchor — owner asks for status, or is about to send a command
- Repo upkeep — repo-level assets above any single journey (managed WITHOUT being asked)
- Communication — four mechanisms and PL session rituals
- TODO.md — the single plan + board
- State files & canonical assets
- Boundaries
Scripts executed separately
scripts/agent-cli-help.tscripts/attempt-gate.shscripts/attempt-gate.tscripts/callsign-transfer-e2e.shscripts/callsign-worktree.tscripts/callsign.shscripts/convergence-watch.shscripts/core-structure.tscripts/docker-env-doctor.shscripts/exec-sentinel.shscripts/exec-sentinel.tscripts/exec-state.shscripts/exec-state.tscripts/exec-trust.shscripts/exec-trust.tscripts/executor-wall.shscripts/executor-wall.tscripts/fence-check.shscripts/general-env-doctor.shscripts/general-env-doctor.tscripts/gpu-watch.shscripts/gpu-watch.tscripts/lane-open.shscripts/lane-open.tscripts/lane-resolve.shscripts/lane-resolve.tscripts/log-watch.shscripts/log-watch.tscripts/on-station-proof.tscripts/portable-paths.tscripts/roster-git.tscripts/roster-reach.tscripts/roster.shscripts/script-running.shscripts/script-running.tscripts/selftest/run-selftest.shscripts/spawn-exec-generation-e2e.shscripts/spawn-exec-help.tscripts/spawn-exec-interactive-e2e.shscripts/spawn-exec-lane-resolve.tscripts/spawn-exec-mission-state-e2e.shscripts/spawn-exec-on-station-e2e.shscripts/spawn-exec-operate.tscripts/spawn-exec.shscripts/todo-close-evidence.tscripts/todo.shscripts/todo.t
Files
SKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesSKILL.mdcore63,182 bytesreferences/callsigns.txtdoc384 bytesreferences/decision-rights.mddoc4,918 bytesreferences/dispatch-template.mddoc39,095 bytesreferences/pocket-card.mddoc1,922 bytesreferences/progress-reporting-hooks.mddoc2,367 bytesreferences/todo-template.mddoc7,030 bytesscripts/agent-cli-help.truns1,276 bytesscripts/attempt-gate.shruns3,701 bytesscripts/attempt-gate.truns4,701 bytesscripts/callsign-transfer-e2e.shruns8,051 bytesscripts/callsign-worktree.truns1,763 bytesscripts/callsign.shruns15,459 bytesscripts/convergence-watch.shruns8,781 bytesscripts/core-structure.truns5,884 bytesscripts/docker-env-doctor.shruns19,505 bytesscripts/exec-sentinel.shruns5,872 bytesscripts/exec-sentinel.truns2,481 bytesscripts/exec-state.shruns19,605 bytesscripts/exec-state.truns22,541 bytesscripts/exec-trust.shruns5,469 bytesscripts/exec-trust.truns6,508 bytesscripts/executor-wall.shruns6,781 bytesscripts/executor-wall.truns9,041 bytesscripts/fence-check.shruns4,511 bytesscripts/general-env-doctor.shruns13,850 bytesscripts/general-env-doctor.truns5,986 bytesscripts/gpu-watch.shruns4,645 bytesscripts/gpu-watch.truns1,521 bytesscripts/lane-open.shruns4,060 bytesscripts/lane-open.truns3,952 bytesscripts/lane-resolve.shruns5,119 bytesscripts/lane-resolve.truns6,959 bytesscripts/log-watch.shruns11,145 bytesscripts/log-watch.truns6,953 bytesscripts/on-station-proof.truns1,730 bytesscripts/portable-paths.truns1,546 bytesscripts/roster-git.truns4,169 bytesscripts/roster-reach.truns2,853 bytesscripts/roster.shruns20,354 bytesscripts/script-running.shruns3,481 bytesscripts/script-running.truns3,809 bytesscripts/selftest/run-selftest.shruns1,231 bytesscripts/spawn-exec-generation-e2e.shruns1,963 bytesscripts/spawn-exec-help.truns2,898 bytesscripts/spawn-exec-interactive-e2e.shruns13,550 bytesscripts/spawn-exec-lane-resolve.truns3,502 bytesscripts/spawn-exec-mission-state-e2e.shruns1,801 bytesscripts/spawn-exec-on-station-e2e.shruns2,286 bytesscripts/spawn-exec-operate.truns9,457 bytesscripts/spawn-exec.shruns37,639 bytesscripts/todo-close-evidence.truns1,211 bytesscripts/todo.shruns36,369 bytesscripts/todo.truns28,474 bytes
Read SKILL.md
# PL — Project Lead
The **owner** is whoever owns the work, often the user.
## Development scope, time, and owner approval
Every development task has a finite wall-time budget covering preparation, implementation,
tests, and reporting. Before launching tests, estimate their duration from available prior
runs of the same command or affected tests; state the source and any uncertainty. If no
prior runtime exists, use a provisional estimate from the visible test scope and proceed
with the smallest useful check. By default do not build estimation machinery, calibration
runs, preflight checks, or kill timers to obtain or enforce this estimate.
Test only the changed behavior and its direct consumers. No full evaluation, unit,pl-analyze
When your agent uses it
PL (Project Lead) role sub-skill for incident analysis and process evaluation. Loaded through the pl core routing table, or when the owner explicitly asks for a retrospective or root-cause write-up; NEVER auto-load from ambient context.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
1,475 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
- Method — evidence first, always from disk
- Root-cause classification → fix location
- Output shape
- Routing the lessons
- Boundaries
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore6,271 bytesSKILL.mdcore6,271 bytesSKILL.mdcore6,271 bytesSKILL.mdcore6,271 bytesSKILL.mdcore6,271 bytesscripts/selftest/run-selftest.shruns1,169 bytes
Read SKILL.md
# PL · Analyze — incident analysis & process evaluation
Scripts named below run as `bash "${PL_SKILL_DIR}/scripts/<name>.sh" ...`, where `PL_SKILL_DIR` is the
absolute path of the `pl` skill directory; set it in the same Bash call. The workspace layout (`ai-doc/...`,
ledgers) is documented in the pl core's State files section; a source that does not exist in this project
is skipped and noted in the analysis.
Sub-skill of the PL role, also usable standalone. Words such as journey, callsign, night shift and
take-over are defined once, in the pl core's Terms glossary. The rules in this file are the PL role's
defaults; a project may choose otherwise.
Invoke when something went
wrong — an escaped bug, a stalled run, a run killed at its time limit, an estimate blowup, a
protocol breach, a close-audit FAIL — or when the owner ("owner" means whoever owns the work, oftenpl-audit
When your agent uses it
PL (Project Lead) role sub-skill for acceptance and close-audit. Loaded ONLY through the pl core routing table; NEVER auto-load from context, never invoke directly.
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
3,351 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
- Report audit (owner pastes an executor report)
- Close-audit — the six points, canonical
- Probe discipline at close
- Estimate reconciliation — at every close
- Triage-ruling reconciliation — at every close
- Acceptance gatekeeping — journeys with a final end-to-end acceptance run (the last gate)
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesSKILL.mdcore14,554 bytesscripts/selftest/run-selftest.shruns1,182 bytes
Read SKILL.md
# PL · Audit — acceptance gatekeeping
Scripts named below run as `bash "${PL_SKILL_DIR}/scripts/<name>.sh" ...`, where `PL_SKILL_DIR` is the
absolute path of the `pl` skill directory; set it in the same Bash call.
Sub-skill of the PL role. The pl core skill invokes this EXPLICITLY when an
executor report lands (the owner asks you to review / audit / find faults; "owner" means whoever owns
the work, often the user), when ANY close signal appears, at estimate reconciliation, and at the final
acceptance gate. Core iron rules bind unchanged — above all iron rule 2: **never trust report prose; what is on
disk counts**. The owner is addressed in the user's own language; agent-to-agent text uses the project's
working language. Canonical scripts: the pl skill's `scripts/`. The workspace layout (`ai-doc/...`, ledgers)
is documented in the pl core's State files section. Words such as journey, callsign, window, night shift
and take-over are defined once, in the pl core's Terms glossary. The rules in this file are the PL role's
defaults; a project may choose otherwise.pl-dispatch
When your agent uses it
PL (Project Lead) role sub-skill for opening and scheduling journeys. Loaded ONLY through the pl core routing table; NEVER auto-load from context, never invoke directly.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
7,579 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
- Writing the dispatch (owner asks for a dispatch prompt or to open work)
- Spawn or keep? — one charter, one agent (core iron rule 7)
- Debug-mode dispatch — one debugger, one close, evidence-fenced not hypothesis-fenced
- Planning-time blast-radius scan
- Scheduling — what to dispatch, and when (owner asks what's next / what to schedule while they are away)
- Supervision capacity — decision-density, not headcount
- Callsigns & window self-labeling
- Launch verification — the dispatch is not done when you send it
- Executor-side card protocol (bound via the dispatch text)
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesSKILL.mdcore31,860 bytesscripts/selftest/run-selftest.shruns1,218 bytes
Read SKILL.md
# PL · Dispatch — opening and scheduling journeys
Scripts named below run as `bash "${PL_SKILL_DIR}/scripts/<name>.sh" ...`, where `PL_SKILL_DIR` is the
absolute path of the `pl` skill directory; set it in the same Bash call. When you write text that an
executor will read, the executor has no `PL_SKILL_DIR`: substitute the absolute path of the pl skill's
`scripts` directory for `<PL_SKILL_DIR>` when you write the dispatch.
Sub-skill of the PL role. The pl core skill invokes this EXPLICITLY when a new
journey opens (the owner asks for a dispatch prompt or to open work; "owner" means whoever owns the work,
often the user), when scheduling is decided (what's next / what to schedule while the owner is away),
or when parallelism/capacity is in question. Core iron rules bind unchanged: never write product code;
never trust report prose — disk over words; the owner is addressed in the user's own language, while
agent-to-agent text uses the project's working language (English by default). Canonical scripts:
the pl skill's `scripts/`; canonical references: the pl skill's `references/`. The workspace layoutpl-env
When your agent uses it
PL role sub-skill — environment doctoring. Loaded ONLY by the pl core via its routing table; NEVER auto-load from context, never invoke directly.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
1,730 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
- Environment self-service
- Keys — the one class that is never an escalation
- Pre-run environment self-check
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesSKILL.mdcore7,328 bytesscripts/selftest/run-selftest.shruns1,150 bytes
Read SKILL.md
# PL · Env — environment self-service
Scripts named below run as `bash "${PL_SKILL_DIR}/scripts/<name>.sh" ...`, where `PL_SKILL_DIR` is the
absolute path of the `pl` skill directory; set it in the same Bash call.
Sub-skill of the PL role. The pl core skill invokes this EXPLICITLY on any
environment doubt: a "not available / missing / down" claim, a restart wish, a
VM/host question, or before opening an evaluation or end-to-end run. Canonical scripts:
the pl skill's `scripts/`. Read the host/VM registry from `${SNO_ROSTER_FILE:-}`;
when unset, report "no roster configured" and continue. The TSV columns are
name, address, kind, purpose, and check; no machine inventory ships with the skill.
Use the repo's documented service-address source when one exists.
Read `${SNO_SECRETS_CMD:-}` for an optional secrets wrapper: one executable path
that accepts a command and its arguments, injects secrets, and preserves its exit status.pl-watch
When your agent uses it
PL (Project Lead) role sub-skill for supervising in-flight executors. Loaded ONLY through the pl core routing table; NEVER auto-load from context, never invoke directly.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
6,799 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Card-handling discipline (PL side of Reach)
- Who rules, and how
- Live log watching — four tiers, four different questions
- Big-run posture — front-run the launch, stop on first red
- Roster anomalies
- Take-over & convergence supervision
- Verification time budget
- GPU liveness probe (optional, only when the run uses a local GPU)
Scripts executed separately
scripts/selftest/run-selftest.sh
Files
SKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesSKILL.mdcore28,456 bytesscripts/selftest/run-selftest.shruns1,231 bytes
Read SKILL.md
# PL · Watch — in-flight supervision & process control
Scripts named below run as `bash "${PL_SKILL_DIR}/scripts/<name>.sh" ...`, where `PL_SKILL_DIR` is the
absolute path of the `pl` skill directory; set it in the same Bash call.
Sub-skill of the PL role. The pl core skill invokes this EXPLICITLY whenever
executors are in flight: a watch fires, a card lands, a stall or convergence
doubt appears, an expensive run is requested, or a GPU phase starts. Core iron
rules bind unchanged: never write product code; never trust report prose — disk
over words; the owner ("owner" means whoever owns the work, often the user) is addressed in the user's own
language, while agent-to-agent text uses the project's working language (English by default). Canonical scripts:
the pl skill's `scripts/`. The workspace layout (`ai-doc/ACTIVE/PL/`, ledgers) is documented in the pl core's
State files section. Design
principle behind everything here: **the machine must lose patienceSkills included
- agentic-walkthrough
- charter
- e2e-environment-preflight
- e2e-red-triage
- first-principles-review
- less-is-more
- owner-intent-audit
- python-coder
- rust-coder
- shellscript-coder
- test-writer
- ts-coder
- agentic-time-estimate
- away-brief
- catch-report
- agentic-walkthrough
- e2e-environment-preflight
- e2e-red-triage
- first-principles-review
- less-is-more
- owner-intent-audit
- peer-review
- test-writer
- codex-coder
- codex-coder
- medic
- python-coder
- rust-coder
- shellscript-coder
- sno-cli
- ts-coder
- rem-reflect
- handoff
- heartbeat
- join-talk
- reach
- rotate-agent
- subscription-quota-check
- charter
- cos
- cos-evolve
- cos-review
- cos-watch
- deliver
- pl
- pl-analyze
- pl-audit
- pl-dispatch
- pl-env
- pl-watch
Repository facts
- License
- Apache-2.0
- Created
- Oct 1, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 611
- Open issues
- 1
- Project activity
- Active
Rank over the last 12 weeks
Now #1,000 · best #815 · down 73 in 30 days
- #976 on Oct 29
- #977 on Oct 30
- #982 from Oct 31 to Nov 1
- #991 on Nov 2
- #997 on Nov 3
- #1,000 since Nov 4
21 earlier periods
- #919 on Sep 27
- #927 on Oct 6
- #964 on Oct 7
- #962 on Oct 9
- #935 on Oct 10
- #942 on Oct 11
- #966 on Oct 12
- #970 on Oct 13
- #989 on Oct 14
- #972 on Oct 15
- #977 on Oct 16
- #954 on Oct 17
- #937 on Oct 18
- #978 on Oct 19
- #982 on Oct 20
- #998 on Oct 21
- #962 on Oct 22
- #920 on Oct 23
- #815 on Oct 24
- #987 on Oct 25
- #952 on Oct 28
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Changed on Nov 4, 2026
New signal: Instruction override signal
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 188 notes
plugins/sno-station-standalone/skills/agentic-walkthrough/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/charter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/charter/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/e2e-environment-preflight/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/e2e-red-triage/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/first-principles-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/first-principles-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/first-principles-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/first-principles-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/first-principles-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/first-principles-review/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/less-is-more/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/owner-intent-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/python-coder/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/sno-station-standalone/skills/ts-coder/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/H-reporting-and-visibility/agentic-time-estimate/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 216 dangerous shell commandsin 70 files: skills/M-build-and-rollout/medic/skill/scripts/medic.t:9 skills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t:12 skills/J-peer-review-and-audit/peer-review/skill/scripts/run-adversarial-review.sh:715 and 67 more
- 2 obfuscation signalsin 1 file: skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec.sh:700
- 463 executable scriptsin 242 files: skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/calibration.t:1 skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/run-selftest.sh:1 skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/time-left:1 and 239 more
- 112 references to secretsin 15 files: skills/J-peer-review-and-audit/peer-review/skill/scripts/run-adversarial-review.sh:353 skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-answer-provider:8 skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.t:10 and 12 more
- No requests to vote in Hot
Show all 993 signals by file
plugins/sno-station-standalone/.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Sno Station Skills contributors", "url": "https://github.com/sno-ai/sno-station-skills" - Network accessline 6
"name": "Sno Station Skills contributors", "url": "https://github.com/sno-ai/sno-station-skills" }, - Network accessline 7
"url": "https://github.com/sno-ai/sno-station-skills" - Network accessline 8
}, "homepage": "https://github.com/sno-ai/sno-station-skills", "repository": "https://github.com/sno-ai/sno-station-skills", - Network accessline 9
"homepage": "https://github.com/sno-ai/sno-station-skills", - Network accessline 10
"repository": "https://github.com/sno-ai/sno-station-skills",
plugins/sno-station-standalone/skills/agentic-walkthrough/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/charter/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/e2e-environment-preflight/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/e2e-red-triage/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/first-principles-review/scripts/extract-prd-handoff.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/sno-station-standalone/skills/first-principles-review/scripts/selftest/run-extractor-test.sh
plugins/sno-station-standalone/skills/first-principles-review/scripts/selftest/run-scenarios.sh
plugins/sno-station-standalone/skills/first-principles-review/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 52
trap 'rm -rf "$temporary"' EXIT - Network accessline 69
write("malformed-json.md", source.replace('{"true_problem"', '{"true_problem":,')) write("question-in-report.md", source.replace("high priority.\n\n## PRD Handoff", "high priority?\n\n## PRD Handoff")) write("accept-url-with-query.txt", sou - Network accessline 70
write("question-in-report.md", source.replace("high priority.\n\n## PRD Handoff", "high priority?\n\n## PRD Handoff")) write("accept-url-with-query.txt", source.replace("high priority.\n\n## PRD Handoff", "high priority. See https://example - Network accessline 71
write("accept-url-with-query.txt", source.replace("high priority.\n\n## PRD Handoff", "high priority. See https://example.com/doc?page=2 for detail.\n\n## PRD Handoff"))
plugins/sno-station-standalone/skills/first-principles-review/scripts/selftest/verify-manual-only.sh
plugins/sno-station-standalone/skills/first-principles-review/scripts/selftest/verify-workflow-policy.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/first-principles-review/scripts/validate-report.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/sno-station-standalone/skills/less-is-more/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/owner-intent-audit/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/owner-intent-audit/scripts/selftest/verify-review-boundary.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/python-coder/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/rust-coder/references/standards.md
- Network accessline 238
- Rust API Guidelines: <https://rust-lang.github.io/api-guidelines/> - Network accessline 239
- Cargo Book: <https://doc.rust-lang.org/cargo/reference/> - Network accessline 240
- Clippy documentation: <https://doc.rust-lang.org/clippy/> - Network accessline 241
- Rustonomicon: <https://doc.rust-lang.org/nomicon/> - Network accessline 242
- Miri: <https://github.com/rust-lang/miri>
plugins/sno-station-standalone/skills/rust-coder/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/shellscript-coder/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/test-writer/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
plugins/sno-station-standalone/skills/ts-coder/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/calibration.t
skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 28
trap 'kill "$wrapper" 2>/dev/null || true; wait "$wrapper" 2>/dev/null || true; rm -rf -- "$fake_bin"' EXIT - Dangerous shell operationline 28
trap 'kill "$wrapper" 2>/dev/null || true; wait "$wrapper" 2>/dev/null || true; rm -rf -- "$fake_bin"' EXIT
skills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/time-left
skills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief
skills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 12
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 12
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 164
rm "$root/inbox-broken" - Dangerous shell operationline 164
rm "$root/inbox-broken" - Dangerous shell operationline 170
rm -f "$root/quota.exit"; quota 25 - Dangerous shell operationline 170
rm -f "$root/quota.exit"; quota 25 - Dangerous shell operationline 195
rm -f "$repo"/notes/many*.state.md - Dangerous shell operationline 195
rm -f "$repo"/notes/many*.state.md - Dangerous shell operationline 236
rm -f "$repo/docs/liar.md"; rm -rf "$repo/docs/liar.proof" - Dangerous shell operationline 236
rm -f "$repo/docs/liar.md"; rm -rf "$repo/docs/liar.proof" - Dangerous shell operationline 240
rm -rf "$root/state/away-brief" - Dangerous shell operationline 240
rm -rf "$root/state/away-brief"
skills/H-reporting-and-visibility/away-brief/skill/scripts/selftest/run-selftest.sh
skills/H-reporting-and-visibility/catch-report/skill/scripts/catch-report
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 174
trap 'rm -rf -- "$work"' EXIT - Dangerous shell operationline 174
trap 'rm -rf -- "$work"' EXIT - Access to secretsline 227
[Credential-related source omitted] - Access to secretsline 227
[Credential-related source omitted]
skills/H-reporting-and-visibility/catch-report/skill/scripts/catch-report.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 7
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 7
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 231
rm "$root/bin/claude" - Dangerous shell operationline 231
rm "$root/bin/claude" - Dangerous shell operationline 247
rm -rf "$root/spread"; mkdir -p "$root/spread/claude/p" "$root/spread/codex" - Dangerous shell operationline 247
rm -rf "$root/spread"; mkdir -p "$root/spread/claude/p" "$root/spread/codex" - Dangerous shell operationline 268
rm -f "$root/bin/claude"; cat >"$root/bin/claude" <<'SH' - Dangerous shell operationline 268
rm -f "$root/bin/claude"; cat >"$root/bin/claude" <<'SH'
skills/H-reporting-and-visibility/catch-report/skill/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/agentic-walkthrough/skill/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/e2e/skills/e2e-environment-preflight/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/e2e/skills/e2e-red-triage/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/extract-prd-handoff.py
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-extractor-test.sh
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-scenarios.sh
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 52
trap 'rm -rf "$temporary"' EXIT - Dangerous shell operationline 52
trap 'rm -rf "$temporary"' EXIT - Network accessline 69
write("malformed-json.md", source.replace('{"true_problem"', '{"true_problem":,')) write("question-in-report.md", source.replace("high priority.\n\n## PRD Handoff", "high priority?\n\n## PRD Handoff")) write("accept-url-with-query.txt", sou - Network accessline 69
write("malformed-json.md", source.replace('{"true_problem"', '{"true_problem":,')) write("question-in-report.md", source.replace("high priority.\n\n## PRD Handoff", "high priority?\n\n## PRD Handoff")) write("accept-url-with-query.txt", sou - Network accessline 70
write("question-in-report.md", source.replace("high priority.\n\n## PRD Handoff", "high priority?\n\n## PRD Handoff")) write("accept-url-with-query.txt", source.replace("high priority.\n\n## PRD Handoff", "high priority. See https://example - Network accessline 70
write("question-in-report.md", source.replace("high priority.\n\n## PRD Handoff", "high priority?\n\n## PRD Handoff")) write("accept-url-with-query.txt", source.replace("high priority.\n\n## PRD Handoff", "high priority. See https://example - Network accessline 71
write("accept-url-with-query.txt", source.replace("high priority.\n\n## PRD Handoff", "high priority. See https://example.com/doc?page=2 for detail.\n\n## PRD Handoff")) - Network accessline 71
write("accept-url-with-query.txt", source.replace("high priority.\n\n## PRD Handoff", "high priority. See https://example.com/doc?page=2 for detail.\n\n## PRD Handoff"))
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/verify-manual-only.sh
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/selftest/verify-workflow-policy.sh
skills/J-peer-review-and-audit/first-principles-review/skill/scripts/validate-report.py
skills/J-peer-review-and-audit/less-is-more/skill/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/owner-intent-audit/skill/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/owner-intent-audit/skill/scripts/selftest/verify-review-boundary.sh
skills/J-peer-review-and-audit/peer-review/skill/SKILL.md
skills/J-peer-review-and-audit/peer-review/skill/references/python-standards.md
skills/J-peer-review-and-audit/peer-review/skill/scripts/lib/sno-model.sh
skills/J-peer-review-and-audit/peer-review/skill/scripts/review-backfill.sh
skills/J-peer-review-and-audit/peer-review/skill/scripts/review-findings.sh
skills/J-peer-review-and-audit/peer-review/skill/scripts/review-receipt.sh
skills/J-peer-review-and-audit/peer-review/skill/scripts/run-adversarial-review.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 353
[Credential-related source omitted] - Access to secretsline 353
[Credential-related source omitted] - Access to secretsline 444
[Credential-related source omitted] - Access to secretsline 444
[Credential-related source omitted] - Access to secretsline 453
[Credential-related source omitted] - Access to secretsline 453
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 454
[Credential-related source omitted] - Access to secretsline 461
[Credential-related source omitted] - Access to secretsline 461
[Credential-related source omitted] - Access to secretsline 462
[Credential-related source omitted] - Access to secretsline 462
[Credential-related source omitted] - Access to secretsline 471
[Credential-related source omitted] - Access to secretsline 471
[Credential-related source omitted] - Access to secretsline 475
[Credential-related source omitted] - Access to secretsline 475
[Credential-related source omitted] - Access to secretsline 582
[Credential-related source omitted] - Access to secretsline 582
[Credential-related source omitted] - Access to secretsline 583
[Credential-related source omitted] - Access to secretsline 583
[Credential-related source omitted] - Access to secretsline 596
[Credential-related source omitted] - Access to secretsline 596
[Credential-related source omitted] - Dangerous shell operationline 715
rm -rf "$SLOT_HELD" - Dangerous shell operationline 715
rm -rf "$SLOT_HELD" - Dangerous shell operationline 738
rm -rf "$slot" - Dangerous shell operationline 738
rm -rf "$slot" - Access to secretsline 762
[Credential-related source omitted] - Access to secretsline 762
[Credential-related source omitted] - Access to secretsline 763
[Credential-related source omitted] - Access to secretsline 763
[Credential-related source omitted] - Access to secretsline 860
[Credential-related source omitted] - Access to secretsline 860
[Credential-related source omitted] - Dangerous shell operationline 936
rm -rf -- "$cursor_tmp" - Dangerous shell operationline 936
rm -rf -- "$cursor_tmp" - Access to secretsline 937
[Credential-related source omitted] - Access to secretsline 937
[Credential-related source omitted] - Access to secretsline 938
[Credential-related source omitted] - Access to secretsline 938
[Credential-related source omitted] - Dangerous shell operationline 1109
rm -f "$PROMPT_TMP" "$STDOUT_TMP" "$STDERR_TMP" - Dangerous shell operationline 1109
rm -f "$PROMPT_TMP" "$STDOUT_TMP" "$STDERR_TMP" - Dangerous shell operationline 1237
rm -rf "$WORKDIR" - Dangerous shell operationline 1237
rm -rf "$WORKDIR"
skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/cursor-process-group.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 6
trap '[[ ! -f "$root/helper.pid" ]] || kill "$(cat "$root/helper.pid")" 2>/dev/null || true; rm -rf -- "$root"' EXIT - Dangerous shell operationline 6
trap '[[ ! -f "$root/helper.pid" ]] || kill "$(cat "$root/helper.pid")" 2>/dev/null || true; rm -rf -- "$root"' EXIT
skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-cross-vendor.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 7
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 7
trap 'rm -rf -- "$root"' EXIT - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 19
[Credential-related source omitted] - Access to secretsline 21
[Credential-related source omitted] - Access to secretsline 21
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Dangerous shell operationline 167
rm -f "$REVIEW_OUTPUT_FILE" - Dangerous shell operationline 167
rm -f "$REVIEW_OUTPUT_FILE"
skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-model-settings.sh
skills/J-peer-review-and-audit/peer-review/skill/scripts/selftest/run-selftest.sh
skills/J-peer-review-and-audit/test-writer/skill/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/codex-coder/overlay/claude/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/codex-coder/overlay/claude/scripts/selftest/text-check.py
skills/M-build-and-rollout/codex-coder/overlay/codex/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/M-build-and-rollout/codex-coder/overlay/codex/scripts/selftest/text-check.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/M-build-and-rollout/medic/skill/scripts/medic
skills/M-build-and-rollout/medic/skill/scripts/medic.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 9
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 9
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 34
rm -rf "$root/fx" "$root/home"; mkdir -p "$root/fx" "$root/home/.claude/skills" "$root/home/.agents/skills" - Dangerous shell operationline 34
rm -rf "$root/fx" "$root/home"; mkdir -p "$root/fx" "$root/home/.claude/skills" "$root/home/.agents/skills" - Dangerous shell operationline 77
good_setup; rm "$root/bin/sno" - Dangerous shell operationline 77
good_setup; rm "$root/bin/sno" - Dangerous shell operationline 81
good_setup; rm "$root/bin/claude" "$root/bin/codex" - Dangerous shell operationline 81
good_setup; rm "$root/bin/claude" "$root/bin/codex" - Dangerous shell operationline 85
good_setup; rm -r "$root/home/.claude/skills/charter" "$root/home/.claude/skills/join-talk" "$root/home/.agents/skills/deliver" - Dangerous shell operationline 85
good_setup; rm -r "$root/home/.claude/skills/charter" "$root/home/.claude/skills/join-talk" "$root/home/.agents/skills/deliver" - Dangerous shell operationline 102
good_setup; rm "$root/bin/codex"; sed -i 's/"codex trust","result":"ok"/"codex trust","result":"changed"/; s/"codex configured","result":"ok"/"codex configured","result":"missing"/' "$root/fx/doctor.json" - Dangerous shell operationline 102
good_setup; rm "$root/bin/codex"; sed -i 's/"codex trust","result":"ok"/"codex trust","result":"changed"/; s/"codex configured","result":"ok"/"codex configured","result":"missing"/' "$root/fx/doctor.json" - Dangerous shell operationline 132
good_setup; rm -r "$root/home/.claude/skills/charter"; before="$(tree_hash)"; run run >/dev/null - Dangerous shell operationline 132
good_setup; rm -r "$root/home/.claude/skills/charter"; before="$(tree_hash)"; run run >/dev/null
skills/M-build-and-rollout/medic/skill/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/python-coder/skill/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/rust-coder/skill/references/standards.md
- Network accessline 238
- Rust API Guidelines: <https://rust-lang.github.io/api-guidelines/> - Network accessline 238
- Rust API Guidelines: <https://rust-lang.github.io/api-guidelines/> - Network accessline 239
- Cargo Book: <https://doc.rust-lang.org/cargo/reference/> - Network accessline 239
- Cargo Book: <https://doc.rust-lang.org/cargo/reference/> - Network accessline 240
- Clippy documentation: <https://doc.rust-lang.org/clippy/> - Network accessline 240
- Clippy documentation: <https://doc.rust-lang.org/clippy/> - Network accessline 241
- Rustonomicon: <https://doc.rust-lang.org/nomicon/> - Network accessline 241
- Rustonomicon: <https://doc.rust-lang.org/nomicon/> - Network accessline 242
- Miri: <https://github.com/rust-lang/miri> - Network accessline 242
- Miri: <https://github.com/rust-lang/miri>
skills/M-build-and-rollout/rust-coder/skill/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/shellscript-coder/skill/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/sno-cli/skill/SKILL.md
skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/run-selftest.sh
skills/M-build-and-rollout/sno-cli/skill/scripts/selftest/text-check.py
skills/M-build-and-rollout/ts-coder/skill/scripts/selftest/run-selftest.sh
skills/R-recursive-self-improvement/rem-reflect/skill/SKILL.md
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/adopt.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/adopt.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/agent-sessions.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/allowance-fallback.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 37
} if (process.env.REM_ALLOWANCE_REFUSED === 'yes') { console.log(JSON.stringify({error:'allowance_used_up',message:'Your weekly allowance is used up.',reset_at:'2026-10-24T17:00:00Z',top_up_url:'https://example.com/top-up'})); - Network accessline 37
} if (process.env.REM_ALLOWANCE_REFUSED === 'yes') { console.log(JSON.stringify({error:'allowance_used_up',message:'Your weekly allowance is used up.',reset_at:'2026-10-24T17:00:00Z',top_up_url:'https://example.com/top-up'})); - Network accessline 38
if (process.env.REM_ALLOWANCE_REFUSED === 'yes') { console.log(JSON.stringify({error:'allowance_used_up',message:'Your weekly allowance is used up.',reset_at:'2026-10-24T17:00:00Z',top_up_url:'https://example.com/top-up'})); process - Network accessline 38
if (process.env.REM_ALLOWANCE_REFUSED === 'yes') { console.log(JSON.stringify({error:'allowance_used_up',message:'Your weekly allowance is used up.',reset_at:'2026-10-24T17:00:00Z',top_up_url:'https://example.com/top-up'})); process - Network accessline 39
console.log(JSON.stringify({error:'allowance_used_up',message:'Your weekly allowance is used up.',reset_at:'2026-10-24T17:00:00Z',top_up_url:'https://example.com/top-up'})); - Network accessline 39
console.log(JSON.stringify({error:'allowance_used_up',message:'Your weekly allowance is used up.',reset_at:'2026-10-24T17:00:00Z',top_up_url:'https://example.com/top-up'})); - Network accessline 145
assert.deepEqual(requests[0].args, ['rem', 'judge', '--json']); assert.ok(requests[1].batch.run_id.startsWith('20261016-0000-local-')); for (const request of requests.slice(1)) { - Network accessline 145
assert.deepEqual(requests[0].args, ['rem', 'judge', '--json']); assert.ok(requests[1].batch.run_id.startsWith('20261016-0000-local-')); for (const request of requests.slice(1)) { - Network accessline 146
assert.ok(requests[1].batch.run_id.startsWith('20261016-0000-local-')); for (const request of requests.slice(1)) { const versions = request.batch.halves.flatMap((half: { sessions: { trace_id: string }[] }) => half.sessions.map(row - Network accessline 146
assert.ok(requests[1].batch.run_id.startsWith('20261016-0000-local-')); for (const request of requests.slice(1)) { const versions = request.batch.halves.flatMap((half: { sessions: { trace_id: string }[] }) => half.sessions.map(row - Network accessline 147
for (const request of requests.slice(1)) { - Network accessline 147
for (const request of requests.slice(1)) { - Network accessline 149
assert.deepEqual(versions, request.batch.run_id === '20261020-0500' ? ['first.v2', 'quiet.v1'] : ['quiet.v1']); } assert.ok(requests.some(request => request.batch.run_id === '20261020-0500')); - Network accessline 149
assert.deepEqual(versions, request.batch.run_id === '20261020-0500' ? ['first.v2', 'quiet.v1'] : ['quiet.v1']); } assert.ok(requests.some(request => request.batch.run_id === '20261020-0500')); - Network accessline 150
} assert.ok(requests.some(request => request.batch.run_id === '20261020-0500')); assert.equal(readLessons(store).length, 3, 'the cloud handles the grown version after reset'); - Network accessline 150
} assert.ok(requests.some(request => request.batch.run_id === '20261020-0500')); assert.equal(readLessons(store).length, 3, 'the cloud handles the grown version after reset'); - Network accessline 151
assert.ok(requests.some(request => request.batch.run_id === '20261020-0500')); - Network accessline 151
assert.ok(requests.some(request => request.batch.run_id === '20261020-0500'));
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/allowance-request-isolation.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/backend.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Access to secretsline 43
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 46
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 115
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted] - Access to secretsline 116
[Credential-related source omitted]
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/calls.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/catalogue-cloud.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/catalogue.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/chunk.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-apply.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-batch.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-day.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-verdict.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud-wait.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cloud.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/config.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Access to secretsline 195
[Credential-related source omitted] - Access to secretsline 195
[Credential-related source omitted] - Access to secretsline 221
[Credential-related source omitted] - Access to secretsline 221
[Credential-related source omitted] - Access to secretsline 223
[Credential-related source omitted] - Access to secretsline 223
[Credential-related source omitted]
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/cursor.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/evidence.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/first-message.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/harvest.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/harvest.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/hermes-openclaw.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/identity.test.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 23
test('normalizeRemote folds scp and https to host/org/repo, drops .git', () => { assert.equal(normalizeRemote('git@github.com:example/project.git'), 'github.com/example/project'); assert.equal(normalizeRemote('https://github.com/example - Network accessline 23
test('normalizeRemote folds scp and https to host/org/repo, drops .git', () => { assert.equal(normalizeRemote('git@github.com:example/project.git'), 'github.com/example/project'); assert.equal(normalizeRemote('https://github.com/example - Network accessline 24
assert.equal(normalizeRemote('git@github.com:example/project.git'), 'github.com/example/project'); assert.equal(normalizeRemote('https://github.com/example/project.git'), 'github.com/example/project'); assert.equal(normalizeRemote('git@ - Network accessline 24
assert.equal(normalizeRemote('git@github.com:example/project.git'), 'github.com/example/project'); assert.equal(normalizeRemote('https://github.com/example/project.git'), 'github.com/example/project'); assert.equal(normalizeRemote('git@ - Network accessline 25
assert.equal(normalizeRemote('https://github.com/example/project.git'), 'github.com/example/project'); - Network accessline 25
assert.equal(normalizeRemote('https://github.com/example/project.git'), 'github.com/example/project');
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/identity.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/installed-roots.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/journey-adopt-lesson.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/journey-ops.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/labeler.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/labeler.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/ledger.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/lessons.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-filter.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-first-output.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-settings.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/local-writer.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/login-in-place.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/model-json.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/no-network.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/observe.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/page-journey.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/pages.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/pages.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer-loop.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer-validate.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/proposer.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall-hook.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/recall.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/reflect.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/reflect.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/rem-reflect
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/rem-reflect.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/render-chunk.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/render.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/report.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/run-status.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/sampling.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/sampling.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest-guard.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/claude
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/codex
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/shim-core.cjs
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/bin/sno
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/fixtures/verdict-traces.json
- Network accessline 377
"tool_use_id": "toolu_01Dy1rM9TAJi1jRzsiLTGaSA", "type": "tool_result", "content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\ - Network accessline 377
"tool_use_id": "toolu_01Dy1rM9TAJi1jRzsiLTGaSA", "type": "tool_result", "content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\ - Network accessline 378
"type": "tool_result", "content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\n333-): ProviderResult {\n334- return {\n335- content - Network accessline 378
"type": "tool_result", "content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\n333-): ProviderResult {\n334- return {\n335- content - Network accessline 379
"content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\n333-): ProviderResult {\n334- return {\n335- content,\n336- model,\n[FAIL] dispa - Network accessline 379
"content": "328:function normalizeResult(\n329- content: string,\n330- model: string,\n331- usage: unknown,\n332- toolCalls: unknown[] | undefined,\n333-): ProviderResult {\n334- return {\n335- content,\n336- model,\n[FAIL] dispa
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/journey-e2e.sh
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/journey.mjs
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/observe-journey.mjs
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 19
trap 'rm -rf -- "$WORK"' EXIT - Dangerous shell operationline 19
trap 'rm -rf -- "$WORK"' EXIT - Dangerous shell operationline 27
ALLOW_PROGRAMS=(node git sh bash env cat uname dirname basename mkdir rm cp mv ln chmod mktemp date sort grep sed head tail wc tr cut readlink) - Dangerous shell operationline 27
ALLOW_PROGRAMS=(node git sh bash env cat uname dirname basename mkdir rm cp mv ln chmod mktemp date sort grep sed head tail wc tr cut readlink) - Dangerous shell operationline 82
[[ -s "$EXEC_LOG" ]] || fail "the shims recorded no exec (the instrument did not run)" - Dangerous shell operationline 82
[[ -s "$EXEC_LOG" ]] || fail "the shims recorded no exec (the instrument did not run)"
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/selftest/spawn-python.mjs
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/session.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/session.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/signal-local.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/skill-impact.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/station-settings.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/store-memory.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/store.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/test-helpers.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/text.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/trigger.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/trigger.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/verdicts.test.ts
skills/R-recursive-self-improvement/rem-reflect/skill/scripts/verdicts.ts
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Dangerous shell operationline 59
// A wrapper's own option (`npx --yes`, `sudo -E`) comes before the command word and is dropped with the wrapper. - Dangerous shell operationline 59
// A wrapper's own option (`npx --yes`, `sudo -E`) comes before the command word and is dropped with the wrapper.
skills/S-communication-and-handoff/handoff/skill/scripts/handoff-checkpoint
skills/S-communication-and-handoff/handoff/skill/scripts/handoff-checkpoint.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 8
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 8
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 91
rm -f -- "$inside" - Dangerous shell operationline 91
rm -f -- "$inside" - Dangerous shell operationline 118
rm -- "$repo/late.txt" - Dangerous shell operationline 118
rm -- "$repo/late.txt"
skills/S-communication-and-handoff/handoff/skill/scripts/selftest/run-selftest.sh
skills/S-communication-and-handoff/handoff/skill/scripts/selftest/text-check.py
skills/S-communication-and-handoff/heartbeat/skill/scripts/selftest/run-selftest.sh
skills/S-communication-and-handoff/heartbeat/skill/scripts/selftest/text-check.py
skills/S-communication-and-handoff/join-talk/skill/scripts/join-talk.sh
skills/S-communication-and-handoff/join-talk/skill/scripts/selftest/run-selftest.sh
skills/S-communication-and-handoff/reach/skill/scripts/selftest/run-selftest.sh
skills/S-communication-and-handoff/reach/skill/scripts/selftest/text-check.py
skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-answer-provider
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 8
[Credential-related source omitted] - Access to secretsline 8
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Access to secretsline 61
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Dangerous shell operationline 64
trap 'rm -rf -- "$tmp"' EXIT - Dangerous shell operationline 64
trap 'rm -rf -- "$tmp"' EXIT - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted]
skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-preflight
skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-resume
skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-resume.t
skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-switch
skills/S-communication-and-handoff/rotate-agent/skill/scripts/rotate-agent-watch
skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/fake-quota
skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/run-selftest.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 22
TMP="$(mktemp -d)"; trap 'rm -rf -- "$TMP"' EXIT - Dangerous shell operationline 22
TMP="$(mktemp -d)"; trap 'rm -rf -- "$TMP"' EXIT - Dangerous shell operationline 80
rm -f "$TMP/watch.state" - Dangerous shell operationline 80
rm -f "$TMP/watch.state"
skills/S-communication-and-handoff/rotate-agent/skill/scripts/selftest/switch-provider.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 7
trap 'rm -rf -- "$TMP"' EXIT - Dangerous shell operationline 7
trap 'rm -rf -- "$TMP"' EXIT - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Dangerous shell operationline 20
rm "$FAKE_ROOT/busy" - Dangerous shell operationline 20
rm "$FAKE_ROOT/busy" - Dangerous shell operationline 23
rm -f "$FAKE_ROOT/screen-busy" - Dangerous shell operationline 23
rm -f "$FAKE_ROOT/screen-busy" - Network accessline 63
printf "INFO [agent-test] agent.turn_context: conversation turn: session=agent-test msg='Review the conversation…'\n" >>"$HERMES_HOME/logs/agent.log" fi jq -nc --arg p "$provider" --arg m "$answer_model" ' - Network accessline 63
printf "INFO [agent-test] agent.turn_context: conversation turn: session=agent-test msg='Review the conversation…'\n" >>"$HERMES_HOME/logs/agent.log" fi jq -nc --arg p "$provider" --arg m "$answer_model" ' - Network accessline 64
fi jq -nc --arg p "$provider" --arg m "$answer_model" ' {type:"user.message",content:"continue"}, - Network accessline 64
fi jq -nc --arg p "$provider" --arg m "$answer_model" ' {type:"user.message",content:"continue"}, - Network accessline 65
jq -nc --arg p "$provider" --arg m "$answer_model" ' - Network accessline 65
jq -nc --arg p "$provider" --arg m "$answer_model" '
skills/S-communication-and-handoff/subscription-quota-check/skill/scripts/selftest/run-selftest.sh
skills/S-communication-and-handoff/subscription-quota-check/skill/scripts/selftest/text-check.py
skills/T-delegation-and-work-orders/charter/skill/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/cos/skills/cos-evolve/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/cos/skills/cos-evolve/scripts/selftest/text-check.py
skills/T-delegation-and-work-orders/cos/skills/cos-review/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/cos/skills/cos-review/scripts/selftest/text-check.py
skills/T-delegation-and-work-orders/cos/skills/cos-watch/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/cos/skills/cos-watch/scripts/selftest/text-check.py
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-claim.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-claim.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 10
trap 'env -u TMUX tmux -L "$socket" kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT - Dangerous shell operationline 10
trap 'env -u TMUX tmux -L "$socket" kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-roster.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 11
trap '[[ -z "$agent" ]] || kill "$agent" 2>/dev/null || true; env -u TMUX tmux -L "$socket" kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT - Dangerous shell operationline 11
trap '[[ -z "$agent" ]] || kill "$agent" 2>/dev/null || true; env -u TMUX tmux -L "$socket" kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT - Dangerous shell operationline 102
rm -- "$root/home/.local/state/pl-heartbeat/example-repo" - Dangerous shell operationline 102
rm -- "$root/home/.local/state/pl-heartbeat/example-repo"
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-screen.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-screen.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 9
trap 'env -u TMUX TMUX_TMPDIR="$root/tmux" tmux kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT - Dangerous shell operationline 9
trap 'env -u TMUX TMUX_TMPDIR="$root/tmux" tmux kill-server >/dev/null 2>&1 || true; rm -r -- "$root"' EXIT
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/cos-since.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-sentinel.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-sentinel.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 6
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -rf -- "$root"' EXIT - Dangerous shell operationline 6
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -rf -- "$root"' EXIT
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/exec-tree-check.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/cos/skills/cos/scripts/selftest/text-check.py
skills/T-delegation-and-work-orders/deliver/skill/scripts/deliver-proof
skills/T-delegation-and-work-orders/deliver/skill/scripts/deliver-proof.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 6
trap 'rm -r -- "$root"' EXIT - Dangerous shell operationline 6
trap 'rm -r -- "$root"' EXIT - Dangerous shell operationline 131
rm -- "$root/see/first.txt" - Dangerous shell operationline 131
rm -- "$root/see/first.txt" - Dangerous shell operationline 139
rm -- "$log" - Dangerous shell operationline 139
rm -- "$log"
skills/T-delegation-and-work-orders/deliver/skill/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl-analyze/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl-audit/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl-dispatch/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl-env/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl-watch/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl/references/progress-reporting-hooks.md
- Network accessline 27
"hooks": [{ "type": "command", "command": "text=$(sno reach remind --as \"$SNO_REACH_ADDR\" 2>/dev/null) || exit 0; [ -n \"$text\" ] || exit 0; jq -nc --arg text \"$text\" '{hookSpecificOutput:{hookEventName:\"UserPromptSubm - Network accessline 27
"hooks": [{ "type": "command", "command": "text=$(sno reach remind --as \"$SNO_REACH_ADDR\" 2>/dev/null) || exit 0; [ -n \"$text\" ] || exit 0; jq -nc --arg text \"$text\" '{hookSpecificOutput:{hookEventName:\"UserPromptSubm - Network accessline 28
"type": "command", "command": "text=$(sno reach remind --as \"$SNO_REACH_ADDR\" 2>/dev/null) || exit 0; [ -n \"$text\" ] || exit 0; jq -nc --arg text \"$text\" '{hookSpecificOutput:{hookEventName:\"UserPromptSubmit\",additionalConte - Network accessline 28
"type": "command", "command": "text=$(sno reach remind --as \"$SNO_REACH_ADDR\" 2>/dev/null) || exit 0; [ -n \"$text\" ] || exit 0; jq -nc --arg text \"$text\" '{hookSpecificOutput:{hookEventName:\"UserPromptSubmit\",additionalConte - Network accessline 29
"command": "text=$(sno reach remind --as \"$SNO_REACH_ADDR\" 2>/dev/null) || exit 0; [ -n \"$text\" ] || exit 0; jq -nc --arg text \"$text\" '{hookSpecificOutput:{hookEventName:\"UserPromptSubmit\",additionalContext:$text}}' || true", - Network accessline 29
"command": "text=$(sno reach remind --as \"$SNO_REACH_ADDR\" 2>/dev/null) || exit 0; [ -n \"$text\" ] || exit 0; jq -nc --arg text \"$text\" '{hookSpecificOutput:{hookEventName:\"UserPromptSubmit\",additionalContext:$text}}' || true", - Network accessline 48
pre_llm_call: - command: >- bash -c 'text=$(sno reach remind --as "$SNO_REACH_ADDR" 2>/dev/null) || exit 0; [ -n "$text" ] || exit 0; jq -nc --arg text "$text" "{context:\$text}" || true' - Network accessline 48
pre_llm_call: - command: >- bash -c 'text=$(sno reach remind --as "$SNO_REACH_ADDR" 2>/dev/null) || exit 0; [ -n "$text" ] || exit 0; jq -nc --arg text "$text" "{context:\$text}" || true' - Network accessline 49
- command: >- bash -c 'text=$(sno reach remind --as "$SNO_REACH_ADDR" 2>/dev/null) || exit 0; [ -n "$text" ] || exit 0; jq -nc --arg text "$text" "{context:\$text}" || true' timeout: 10 - Network accessline 49
- command: >- bash -c 'text=$(sno reach remind --as "$SNO_REACH_ADDR" 2>/dev/null) || exit 0; [ -n "$text" ] || exit 0; jq -nc --arg text "$text" "{context:\$text}" || true' timeout: 10 - Network accessline 50
bash -c 'text=$(sno reach remind --as "$SNO_REACH_ADDR" 2>/dev/null) || exit 0; [ -n "$text" ] || exit 0; jq -nc --arg text "$text" "{context:\$text}" || true' - Network accessline 50
bash -c 'text=$(sno reach remind --as "$SNO_REACH_ADDR" 2>/dev/null) || exit 0; [ -n "$text" ] || exit 0; jq -nc --arg text "$text" "{context:\$text}" || true'
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/agent-cli-help.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/attempt-gate.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/attempt-gate.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign-transfer-e2e.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 15
fresh() { export HOME="$BASE/$1"; rm -rf "$HOME"; mkdir -p "$HOME/.local/state"; } - Dangerous shell operationline 15
fresh() { export HOME="$BASE/$1"; rm -rf "$HOME"; mkdir -p "$HOME/.local/state"; } - Dangerous shell operationline 163
rm -rf "$BASE" - Dangerous shell operationline 163
rm -rf "$BASE"
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign-worktree.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/callsign.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/convergence-watch.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/core-structure.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/docker-env-doctor.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Network accessline 45
die() { echo "docker-env-doctor: $*" >&2; exit 2; } for tool in docker jq grep curl find date flock mktemp ss; do - Network accessline 45
die() { echo "docker-env-doctor: $*" >&2; exit 2; } for tool in docker jq grep curl find date flock mktemp ss; do - Network accessline 46
for tool in docker jq grep curl find date flock mktemp ss; do - Network accessline 46
for tool in docker jq grep curl find date flock mktemp ss; do - Network accessline 267
HPORTS=$(printf '%s\n' "$MAPPINGS" | grep -oE '[0-9]+$' | sort -u || true) CPORTS=$(printf '%s\n' "$PORTMAP" | awk -F'/' 'NF>1 {print $1}' | sort -u) probe_addr() { # map a bind address to something curl can reach - Network accessline 267
HPORTS=$(printf '%s\n' "$MAPPINGS" | grep -oE '[0-9]+$' | sort -u || true) CPORTS=$(printf '%s\n' "$PORTMAP" | awk -F'/' 'NF>1 {print $1}' | sort -u) probe_addr() { # map a bind address to something curl can reach - Network accessline 268
CPORTS=$(printf '%s\n' "$PORTMAP" | awk -F'/' 'NF>1 {print $1}' | sort -u) probe_addr() { # map a bind address to something curl can reach case "$1" in 0.0.0.0|'[::]'|::) echo "127.0.0.1" ;; \[*\]) printf '%s' "$1" ;; *) printf '%s' "$1" - Network accessline 268
CPORTS=$(printf '%s\n' "$PORTMAP" | awk -F'/' 'NF>1 {print $1}' | sort -u) probe_addr() { # map a bind address to something curl can reach case "$1" in 0.0.0.0|'[::]'|::) echo "127.0.0.1" ;; \[*\]) printf '%s' "$1" ;; *) printf '%s' "$1" - Network accessline 269
probe_addr() { # map a bind address to something curl can reach - Network accessline 269
probe_addr() { # map a bind address to something curl can reach - Network accessline 275
for m in $MAPPINGS; do p="${m##*:}"; a=$(probe_addr "${m%:*}") HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true) - Network accessline 275
for m in $MAPPINGS; do p="${m##*:}"; a=$(probe_addr "${m%:*}") HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true) - Network accessline 276
p="${m##*:}"; a=$(probe_addr "${m%:*}") HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true) HTTP="${HTTP:-000}" - Network accessline 276
p="${m##*:}"; a=$(probe_addr "${m%:*}") HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true) HTTP="${HTTP:-000}" - Network accessline 277
HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true) - Network accessline 277
HTMP=$(mktemp); HTTP=$(curl -s -m 3 -o "$HTMP" -w '%{http_code}' "http://$a:$p/health" 2>/dev/null || true) - Dangerous shell operationline 289
rm -f "$HTMP"; break - Dangerous shell operationline 289
rm -f "$HTMP"; break - Dangerous shell operationline 292
rm -f "$HTMP" - Dangerous shell operationline 292
rm -f "$HTMP"
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-sentinel.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-sentinel.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 6
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -rf -- "$root"' EXIT - Dangerous shell operationline 6
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -rf -- "$root"' EXIT
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-state.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Network accessline 133
emit_state() { if [[ "$as_json" == yes ]]; then jq -nc --arg cs "$callsign" --arg st "$state" --arg d "$detail" \ - Network accessline 133
emit_state() { if [[ "$as_json" == yes ]]; then jq -nc --arg cs "$callsign" --arg st "$state" --arg d "$detail" \ - Network accessline 134
if [[ "$as_json" == yes ]]; then jq -nc --arg cs "$callsign" --arg st "$state" --arg d "$detail" \ --arg a "$argv" --arg p "$pane" --arg rt "$runtime" --arg turn "$turn" \ - Network accessline 134
if [[ "$as_json" == yes ]]; then jq -nc --arg cs "$callsign" --arg st "$state" --arg d "$detail" \ --arg a "$argv" --arg p "$pane" --arg rt "$runtime" --arg turn "$turn" \ - Network accessline 135
jq -nc --arg cs "$callsign" --arg st "$state" --arg d "$detail" \ - Network accessline 135
jq -nc --arg cs "$callsign" --arg st "$state" --arg d "$detail" \
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-state.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-trust.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Instruction override signalline 18
# - records the installed claude version as lastOnboardingVersion. # Keys are only added or overwritten, never removed. Executors launched by spawn-exec.sh # with --runtime claude run `claude --dangerously-skip-permissions` (and codex run - Instruction override signalline 18
# - records the installed claude version as lastOnboardingVersion. # Keys are only added or overwritten, never removed. Executors launched by spawn-exec.sh # with --runtime claude run `claude --dangerously-skip-permissions` (and codex run - Instruction override signalline 19
# Keys are only added or overwritten, never removed. Executors launched by spawn-exec.sh # with --runtime claude run `claude --dangerously-skip-permissions` (and codex runs with # --dangerously-bypass-approvals-and-sandbox): no permission p - Instruction override signalline 19
# Keys are only added or overwritten, never removed. Executors launched by spawn-exec.sh # with --runtime claude run `claude --dangerously-skip-permissions` (and codex runs with # --dangerously-bypass-approvals-and-sandbox): no permission p - Instruction override signalline 20
# with --runtime claude run `claude --dangerously-skip-permissions` (and codex runs with - Instruction override signalline 20
# with --runtime claude run `claude --dangerously-skip-permissions` (and codex runs with - Dangerous shell operationline 99
rm -f -- "$tmp"; printf 'exec-trust: failed to write %s\n' "$config" >&2; exec 9>&-; exit 65; } - Dangerous shell operationline 99
rm -f -- "$tmp"; printf 'exec-trust: failed to write %s\n' "$config" >&2; exec 9>&-; exit 65; }
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/exec-trust.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 28
# The runtime can still be writing under $root as it dies, so the first rm can - Dangerous shell operationline 28
# The runtime can still be writing under $root as it dies, so the first rm can - Dangerous shell operationline 29
# lose that race. Under set -e a failed rm aborts the trap and becomes the - Dangerous shell operationline 29
# lose that race. Under set -e a failed rm aborts the trap and becomes the - Dangerous shell operationline 34
rm -rf -- "$root" 2>/dev/null || { sleep 1; rm -rf -- "$root" 2>/dev/null || true; } - Dangerous shell operationline 34
rm -rf -- "$root" 2>/dev/null || { sleep 1; rm -rf -- "$root" 2>/dev/null || true; } - Instruction override signalline 98
marker="TRUST-ROUTE-WORKS-$$" tmux new-session -d -s "$session" -x 200 -y 50 \ "cd $(printf '%q' "$work") && CLAUDE_CONFIG_DIR=$(printf '%q' "$cfg") claude --dangerously-skip-permissions" - Instruction override signalline 98
marker="TRUST-ROUTE-WORKS-$$" tmux new-session -d -s "$session" -x 200 -y 50 \ "cd $(printf '%q' "$work") && CLAUDE_CONFIG_DIR=$(printf '%q' "$cfg") claude --dangerously-skip-permissions" - Instruction override signalline 99
tmux new-session -d -s "$session" -x 200 -y 50 "cd $(printf '%q' "$work") && CLAUDE_CONFIG_DIR=$(printf '%q' "$cfg") claude --dangerously-skip-permissions" - Instruction override signalline 99
tmux new-session -d -s "$session" -x 200 -y 50 "cd $(printf '%q' "$work") && CLAUDE_CONFIG_DIR=$(printf '%q' "$cfg") claude --dangerously-skip-permissions" - Instruction override signalline 100
"cd $(printf '%q' "$work") && CLAUDE_CONFIG_DIR=$(printf '%q' "$cfg") claude --dangerously-skip-permissions" - Instruction override signalline 100
"cd $(printf '%q' "$work") && CLAUDE_CONFIG_DIR=$(printf '%q' "$cfg") claude --dangerously-skip-permissions"
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/executor-wall.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Network accessline 68
exec {lock_fd}>>"$events_lock" flock -x "$lock_fd" jq -nc \ - Network accessline 68
exec {lock_fd}>>"$events_lock" flock -x "$lock_fd" jq -nc \ - Network accessline 69
flock -x "$lock_fd" jq -nc \ --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \ - Network accessline 69
flock -x "$lock_fd" jq -nc \ --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \ - Network accessline 70
jq -nc \ - Network accessline 70
jq -nc \
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/executor-wall.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/fence-check.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Network accessline 44
warn() { say "[WARN] $*"; } fail() { say "[FAIL] $*"; FAILS=$((FAILS+1)); } tcp() { timeout 3 bash -c "exec 3<>/dev/tcp/$1/$2" 2>/dev/null; } - Network accessline 44
warn() { say "[WARN] $*"; } fail() { say "[FAIL] $*"; FAILS=$((FAILS+1)); } tcp() { timeout 3 bash -c "exec 3<>/dev/tcp/$1/$2" 2>/dev/null; } - Dangerous shell operationline 46
tcp() { timeout 3 bash -c "exec 3<>/dev/tcp/$1/$2" 2>/dev/null; } - Dangerous shell operationline 46
tcp() { timeout 3 bash -c "exec 3<>/dev/tcp/$1/$2" 2>/dev/null; } - Network accessline 46
tcp() { timeout 3 bash -c "exec 3<>/dev/tcp/$1/$2" 2>/dev/null; } - Network accessline 46
tcp() { timeout 3 bash -c "exec 3<>/dev/tcp/$1/$2" 2>/dev/null; } - Network accessline 87
[Credential-related source omitted] - Network accessline 87
[Credential-related source omitted] - Network accessline 88
[Credential-related source omitted] - Network accessline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Network accessline 89
[Credential-related source omitted] - Network accessline 89
[Credential-related source omitted] - Network accessline 126
local endpoint="${OPENAI_BASE_URL:-}" [ -n "$endpoint" ] || { warn "connectivity: using the harness's own endpoint"; return; } if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then - Network accessline 126
local endpoint="${OPENAI_BASE_URL:-}" [ -n "$endpoint" ] || { warn "connectivity: using the harness's own endpoint"; return; } if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then - Network accessline 127
[ -n "$endpoint" ] || { warn "connectivity: using the harness's own endpoint"; return; } if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then pass "connectivity: configured OpenAI-compatible endpoint reachable" - Network accessline 127
[ -n "$endpoint" ] || { warn "connectivity: using the harness's own endpoint"; return; } if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then pass "connectivity: configured OpenAI-compatible endpoint reachable" - Network accessline 128
if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then - Network accessline 128
if curl -sf -m 5 "${endpoint%/}/models" >/dev/null 2>&1; then - Dangerous shell operationline 216
if [ "$FIX" -eq 1 ]; then rm -f "$root/.git/index.lock" && fixed "workspace: removed stale git index.lock (no live git process, >5min old)" - Dangerous shell operationline 216
if [ "$FIX" -eq 1 ]; then rm -f "$root/.git/index.lock" && fixed "workspace: removed stale git index.lock (no live git process, >5min old)" - Dangerous shell operationline 217
else fail "workspace: stale git index.lock (no live git process, >5min old) — run: rm $root/.git/index.lock"; fi - Dangerous shell operationline 217
else fail "workspace: stale git index.lock (no live git process, >5min old) — run: rm $root/.git/index.lock"; fi
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/general-env-doctor.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 7
trap 'rm -r -- "$root"' EXIT - Dangerous shell operationline 7
trap 'rm -r -- "$root"' EXIT - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 10
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 40
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Network accessline 85
chmod +x "$root/bin/curl" export PATH="$root/bin:$PATH" CURL_ARGS_FILE="$root/curl.args" export OPENAI_BASE_URL='http://localhost:0/' - Network accessline 85
chmod +x "$root/bin/curl" export PATH="$root/bin:$PATH" CURL_ARGS_FILE="$root/curl.args" export OPENAI_BASE_URL='http://localhost:0/' - Network accessline 86
export PATH="$root/bin:$PATH" CURL_ARGS_FILE="$root/curl.args" export OPENAI_BASE_URL='http://localhost:0/' bash "$scripts_dir/general-env-doctor.sh" connectivity >"$root/out" - Network accessline 86
export PATH="$root/bin:$PATH" CURL_ARGS_FILE="$root/curl.args" export OPENAI_BASE_URL='http://localhost:0/' bash "$scripts_dir/general-env-doctor.sh" connectivity >"$root/out" - Network accessline 87
export OPENAI_BASE_URL='http://localhost:0/' bash "$scripts_dir/general-env-doctor.sh" connectivity >"$root/out" grep -Fxq 'http://localhost:0/models' "$root/curl.args" - Network accessline 87
export OPENAI_BASE_URL='http://localhost:0/' bash "$scripts_dir/general-env-doctor.sh" connectivity >"$root/out" grep -Fxq 'http://localhost:0/models' "$root/curl.args" - Network accessline 88
bash "$scripts_dir/general-env-doctor.sh" connectivity >"$root/out" grep -Fxq 'http://localhost:0/models' "$root/curl.args" grep -Fxq '[PASS] connectivity: configured OpenAI-compatible endpoint reachable' "$root/out" - Network accessline 88
bash "$scripts_dir/general-env-doctor.sh" connectivity >"$root/out" grep -Fxq 'http://localhost:0/models' "$root/curl.args" grep -Fxq '[PASS] connectivity: configured OpenAI-compatible endpoint reachable' "$root/out" - Network accessline 89
grep -Fxq 'http://localhost:0/models' "$root/curl.args" - Network accessline 89
grep -Fxq 'http://localhost:0/models' "$root/curl.args"
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/gpu-watch.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/gpu-watch.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-open.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-open.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-resolve.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/lane-resolve.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/log-watch.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/log-watch.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 18
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -rf -- "$root"' EXIT - Dangerous shell operationline 18
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -rf -- "$root"' EXIT
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/on-station-proof.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/portable-paths.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster-git.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster-reach.t
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 7
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -r -- "$root"' EXIT - Dangerous shell operationline 7
trap 'tmux kill-session -t "$session" 2>/dev/null || true; rm -r -- "$root"' EXIT - Network accessline 10
mkdir -p "$HOME/.local/state" "$root/repo" name="$(bash "$script_dir/callsign.sh" claim --journey j-roster --repo "$root/repo" --kind executor)" jq -nc --arg name "$name" --arg repo "$root/repo" \ - Network accessline 10
mkdir -p "$HOME/.local/state" "$root/repo" name="$(bash "$script_dir/callsign.sh" claim --journey j-roster --repo "$root/repo" --kind executor)" jq -nc --arg name "$name" --arg repo "$root/repo" \ - Network accessline 11
name="$(bash "$script_dir/callsign.sh" claim --journey j-roster --repo "$root/repo" --kind executor)" jq -nc --arg name "$name" --arg repo "$root/repo" \ '{callsign:$name,journey:"j-roster",repo:$repo,pid:999999,ack_due:"2020-01-01T00:0 - Network accessline 11
name="$(bash "$script_dir/callsign.sh" claim --journey j-roster --repo "$root/repo" --kind executor)" jq -nc --arg name "$name" --arg repo "$root/repo" \ '{callsign:$name,journey:"j-roster",repo:$repo,pid:999999,ack_due:"2020-01-01T00:0 - Network accessline 12
jq -nc --arg name "$name" --arg repo "$root/repo" \ - Network accessline 12
jq -nc --arg name "$name" --arg repo "$root/repo" \ - Network accessline 40
utf_name="$(bash "$script_dir/callsign.sh" claim --journey j-utf --repo "$root/repo" --kind executor)" jq -nc --arg name "$utf_name" --arg repo "$root/repo" \ - Network accessline 40
utf_name="$(bash "$script_dir/callsign.sh" claim --journey j-utf --repo "$root/repo" --kind executor)" jq -nc --arg name "$utf_name" --arg repo "$root/repo" \ - Network accessline 41
jq -nc --arg name "$utf_name" --arg repo "$root/repo" \ - Network accessline 41
jq -nc --arg name "$utf_name" --arg repo "$root/repo" \
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/roster.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/script-running.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/script-running.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/selftest/run-selftest.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-generation-e2e.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-help.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-interactive-e2e.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 39
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 39
trap 'rm -rf -- "$root"' EXIT - Dangerous shell operationline 148
trap 'reap; rm -rf -- "$root"' EXIT - Dangerous shell operationline 148
trap 'reap; rm -rf -- "$root"' EXIT
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-lane-resolve.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-mission-state-e2e.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-on-station-e2e.sh
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec-operate.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/spawn-exec.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
#!/usr/bin/env bash - Instruction override signalline 43
# Mid-run instructions travel through the executor's Reach address. The runtime # runs without its own sandbox or approval prompts (codex --dangerously-bypass- # approvals-and-sandbox, claude --dangerously-skip-permissions): - Instruction override signalline 43
# Mid-run instructions travel through the executor's Reach address. The runtime # runs without its own sandbox or approval prompts (codex --dangerously-bypass- # approvals-and-sandbox, claude --dangerously-skip-permissions): - Instruction override signalline 44
# runs without its own sandbox or approval prompts (codex --dangerously-bypass- # approvals-and-sandbox, claude --dangerously-skip-permissions): the guardrails are # the wall and fence-check.sh instead, so use it only in a re - Instruction override signalline 44
# runs without its own sandbox or approval prompts (codex --dangerously-bypass- # approvals-and-sandbox, claude --dangerously-skip-permissions): the guardrails are # the wall and fence-check.sh instead, so use it only in a re - Instruction override signalline 45
# approvals-and-sandbox, claude --dangerously-skip-permissions): the guardrails are - Instruction override signalline 45
# approvals-and-sandbox, claude --dangerously-skip-permissions): the guardrails are - Dangerous shell operationline 320
rm -f -- "$startup_file" - Dangerous shell operationline 320
rm -f -- "$startup_file" - Dangerous shell operationline 376
# background command's expansions in the forked child, so an early rm of the - Dangerous shell operationline 376
# background command's expansions in the forked child, so an early rm of the - Dangerous shell operationline 380
rm -f "$merged" - Dangerous shell operationline 380
rm -f "$merged" - Dangerous shell operationline 410
rm -f -- "$wall_events" "$wall_events.lock" - Dangerous shell operationline 410
rm -f -- "$wall_events" "$wall_events.lock" - Network accessline 456
if [ "$current" = "current" ]; then if [ "$mode" = "runtime" ] && [ "$operation" != "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 456
if [ "$current" = "current" ]; then if [ "$mode" = "runtime" ] && [ "$operation" != "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 457
if [ "$mode" = "runtime" ] && [ "$operation" != "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ --arg o "$owner" --arg sid "$spawn_id" --arg cs "$callsign" \ - Network accessline 457
if [ "$mode" = "runtime" ] && [ "$operation" != "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ --arg o "$owner" --arg sid "$spawn_id" --arg cs "$callsign" \ - Network accessline 458
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 458
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 462
>> "$missions" elif [ "$operation" = "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 462
>> "$missions" elif [ "$operation" = "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 463
elif [ "$operation" = "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ --arg o "$owner" --arg sid "$spawn_id" --arg cs "$callsign" \ - Network accessline 463
elif [ "$operation" = "delegate" ]; then jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ --arg o "$owner" --arg sid "$spawn_id" --arg cs "$callsign" \ - Network accessline 464
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 464
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 468
>> "$missions" else jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 468
>> "$missions" else jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 469
else jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ --arg o "$owner" --arg st "$success_test" --arg ev "$evidence" \ - Network accessline 469
else jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ --arg o "$owner" --arg st "$success_test" --arg ev "$evidence" \ - Network accessline 470
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Network accessline 470
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$mission" \ - Dangerous shell operationline 506
rm -f -- "$state_file" - Dangerous shell operationline 506
rm -f -- "$state_file" - Network accessline 514
write_startup_receipt() { local state="$1" reason="${2:-}" tmp="${startup_file}.tmp.$$" jq -nc --arg sid "$startup_spawn_id" --arg state "$state" --arg reason "$reason" \ - Network accessline 514
write_startup_receipt() { local state="$1" reason="${2:-}" tmp="${startup_file}.tmp.$$" jq -nc --arg sid "$startup_spawn_id" --arg state "$state" --arg reason "$reason" \ - Network accessline 515
local state="$1" reason="${2:-}" tmp="${startup_file}.tmp.$$" jq -nc --arg sid "$startup_spawn_id" --arg state "$state" --arg reason "$reason" \ '{spawn_id:$sid,state:$state,reason:$reason}' >"$tmp" || return 1 - Network accessline 515
local state="$1" reason="${2:-}" tmp="${startup_file}.tmp.$$" jq -nc --arg sid "$startup_spawn_id" --arg state "$state" --arg reason "$reason" \ '{spawn_id:$sid,state:$state,reason:$reason}' >"$tmp" || return 1 - Network accessline 516
jq -nc --arg sid "$startup_spawn_id" --arg state "$state" --arg reason "$reason" \ - Network accessline 516
jq -nc --arg sid "$startup_spawn_id" --arg state "$state" --arg reason "$reason" \ - Instruction override signalline 536
case "$runtime" in codex) printf ' codex --dangerously-bypass-approvals-and-sandbox %s \\\n' "$resume_line" ;; claude) printf ' claude --dangerously-skip-permissions %s \\\n' "$resume_line" ;; - Instruction override signalline 536
case "$runtime" in codex) printf ' codex --dangerously-bypass-approvals-and-sandbox %s \\\n' "$resume_line" ;; claude) printf ' claude --dangerously-skip-permissions %s \\\n' "$resume_line" ;; - Instruction override signalline 537
codex) printf ' codex --dangerously-bypass-approvals-and-sandbox %s \\\n' "$resume_line" ;; claude) printf ' claude --dangerously-skip-permissions %s \\\n' "$resume_line" ;; hermes) printf ' hermes chat --yolo --query \\\n' ;; - Instruction override signalline 537
codex) printf ' codex --dangerously-bypass-approvals-and-sandbox %s \\\n' "$resume_line" ;; claude) printf ' claude --dangerously-skip-permissions %s \\\n' "$resume_line" ;; hermes) printf ' hermes chat --yolo --query \\\n' ;; - Instruction override signalline 538
claude) printf ' claude --dangerously-skip-permissions %s \\\n' "$resume_line" ;; - Instruction override signalline 538
claude) printf ' claude --dangerously-skip-permissions %s \\\n' "$resume_line" ;; - Network accessline 568
mission_event="$( jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" --arg e "$m_op" \ - Network accessline 568
mission_event="$( jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" --arg e "$m_op" \ - Network accessline 569
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" --arg e "$m_op" \ - Network accessline 569
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" --arg e "$m_op" \ - Network accessline 575
if [ -n "$resume" ]; then session_binding_event="$( jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" \ - Network accessline 575
if [ -n "$resume" ]; then session_binding_event="$( jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" \ - Network accessline 576
session_binding_event="$( jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" \ --arg o "$m_owner" --arg cs "$callsign" --arg sid "$mission_spawn_id" \ - Network accessline 576
session_binding_event="$( jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" \ --arg o "$m_owner" --arg cs "$callsign" --arg sid "$mission_spawn_id" \ - Network accessline 577
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" \ - Network accessline 577
jq -nc --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg m "$m_id" \ - Possible obfuscationline 700
printf '{"ts":"%s","pid":%d,"callsign":"%s","journey":"%s","repo":"%s","budget_h":%s,"class":"%s","t_budget":"%s","t_grace":"%s","ack_due":"%s","conv_due":"%s","fence":"%s","log":"%s","resume":"%s","runtime":"%s","addr":"%s","pane":"%s","st - Possible obfuscationline 700
printf '{"ts":"%s","pid":%d,"callsign":"%s","journey":"%s","repo":"%s","budget_h":%s,"class":"%s","t_budget":"%s","t_grace":"%s","ack_due":"%s","conv_due":"%s","fence":"%s","log":"%s","resume":"%s","runtime":"%s","addr":"%s","pane":"%s","st
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo-close-evidence.t
skills/T-delegation-and-work-orders/pl/skills/pl/scripts/todo.sh
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
- Executable script in code of a file that runsagentic-walkthrough/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runscharter/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runse2e-environment-preflight/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runse2e-red-triage/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/extract-prd-handoff.py:1High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/selftest/run-extractor-test.sh:1High confidence
- Dangerous shell operation in code of a file that runsfirst-principles-review/scripts/selftest/run-extractor-test.sh:12High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/selftest/run-scenarios.sh:1High confidence
- Dangerous shell operation in code of a file that runsfirst-principles-review/scripts/selftest/run-scenarios.sh:13High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/selftest/run-selftest.sh:1High confidence
- Dangerous shell operation in code of a file that runsfirst-principles-review/scripts/selftest/run-selftest.sh:52High confidence
- Network access in code of a file that runsfirst-principles-review/scripts/selftest/run-selftest.sh:69High confidence
- Network access in code of a file that runsfirst-principles-review/scripts/selftest/run-selftest.sh:70High confidence
- Network access in code of a file that runsfirst-principles-review/scripts/selftest/run-selftest.sh:71High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/selftest/verify-manual-only.sh:1High confidence
- Dangerous shell operation in code of a file that runsfirst-principles-review/scripts/selftest/verify-manual-only.sh:9High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/selftest/verify-workflow-policy.sh:1High confidence
- Executable script in code of a file that runsfirst-principles-review/scripts/validate-report.py:1High confidence
- Executable script in code of a file that runsless-is-more/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsowner-intent-audit/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsowner-intent-audit/scripts/selftest/verify-review-boundary.sh:1High confidence
- Executable script in code of a file that runspython-coder/scripts/selftest/run-selftest.sh:1High confidence
- Network access in prose of documentationrust-coder/references/standards.md:238Low confidence
- Network access in prose of documentationrust-coder/references/standards.md:239Low confidence
- Network access in prose of documentationrust-coder/references/standards.md:240Low confidence
- Network access in prose of documentationrust-coder/references/standards.md:241Low confidence
- Network access in prose of documentationrust-coder/references/standards.md:242Low confidence
- Executable script in code of a file that runsrust-coder/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsshellscript-coder/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runstest-writer/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsts-coder/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsskills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/calibration.t:1High confidence
- Executable script in code of a file that runsskill/scripts/selftest/calibration.t:1High confidence
- Dangerous shell operation in code of a file that runsskills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/calibration.t:15High confidence
- Dangerous shell operation in code of a file that runsskill/scripts/selftest/calibration.t:15High confidence
- Executable script in code of a file that runsskills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/run-selftest.sh:1High confidence
- Executable script in code of a file that runsskill/scripts/selftest/run-selftest.sh:1High confidence
- Dangerous shell operation in code of a file that runsskills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/selftest/run-selftest.sh:28High confidence
- Dangerous shell operation in code of a file that runsskill/scripts/selftest/run-selftest.sh:28High confidence
- Executable script in code of a file that runsskills/H-reporting-and-visibility/agentic-time-estimate/skill/scripts/time-left:1High confidence
- Executable script in code of a file that runsskill/scripts/time-left:1High confidence
- Executable script in code of a file that runsskills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief:1High confidence
- Executable script in code of a file that runsskill/scripts/away-brief:1High confidence
- Executable script in code of a file that runsskills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t:1High confidence
- Executable script in code of a file that runsskill/scripts/away-brief.t:1High confidence
- Dangerous shell operation in code of a file that runsskills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t:12High confidence
- Dangerous shell operation in code of a file that runsskill/scripts/away-brief.t:12High confidence
- Dangerous shell operation in code of a file that runsskills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t:164High confidence
- Dangerous shell operation in code of a file that runsskill/scripts/away-brief.t:164High confidence
- Dangerous shell operation in code of a file that runsskills/H-reporting-and-visibility/away-brief/skill/scripts/away-brief.t:170High 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/sno-station-standalone/skills/agentic-walkthrough/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/sno-station-standalone/skills/agentic-walkthrough/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/sno-station-standalone/skills/agentic-walkthrough/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/sno-station-standalone/skills/agentic-walkthrough/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.
