Individual skill
poteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Invoke explicitly with $poteto-mode.
skills/poteto-mode/SKILL.md
Source commit d5b20bce6f0602e3155960b5ea46e47fa0692ad2
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 105
- Repository last updated
- Nov 6, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- codex Repository topic
- codex-plugin Repository topic
- developer-tools Repository topic
- engineering-workflows Repository topic
- pstack Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 20,647 bytesagents/openai.yamlasset · 260 bytesplaybooks/authoring-a-skill.mddoc · 1,055 bytesplaybooks/autonomous-run.mddoc · 2,269 bytesplaybooks/autopilot-full.mddoc · 5,852 bytesplaybooks/autopilot-stack.mddoc · 4,127 bytesplaybooks/babysit.mddoc · 8,043 bytesplaybooks/bug-fix.mddoc · 2,814 bytesplaybooks/eval.mddoc · 3,052 bytesplaybooks/feature.mddoc · 3,123 bytesplaybooks/hillclimb.mddoc · 4,765 bytesplaybooks/investigation.mddoc · 1,240 bytesplaybooks/multi-phase-plan.mddoc · 11,676 bytesplaybooks/opening-a-pr.mddoc · 4,666 bytesplaybooks/orchestrate.mddoc · 16,284 bytesplaybooks/pause-safely.mddoc · 1,579 bytesplaybooks/perf-issue.mddoc · 1,556 bytesplaybooks/prototype.mddoc · 2,648 bytesplaybooks/refactoring.mddoc · 4,128 bytesplaybooks/runtime-forensics.mddoc · 1,505 bytesplaybooks/session-pickup.mddoc · 2,047 bytesplaybooks/shipping.mddoc · 5,931 bytesplaybooks/trace-forensics.mddoc · 2,184 bytesplaybooks/visual-parity.mddoc · 1,475 bytesplaybooks/worktree-cleanup.mddoc · 2,736 bytesreferences/bugbot-triage.mddoc · 9,604 bytesreferences/codex-agent-runtime.mddoc · 6,293 bytesreferences/poteto-agent-prompt.mddoc · 812 bytesscripts/bootstrap.tsruns · 3,859 bytesscripts/bun.lockasset · 6,683 bytesscripts/check-plan.mjsruns · 8,203 bytesscripts/check-plan.test.tsruns · 3,336 bytesscripts/orch/orchruns · 244 bytesscripts/orch/orch.test.tsruns · 23,415 bytesscripts/orch/orch.tsruns · 15,830 bytesscripts/orch/store.tsruns · 46,154 bytesscripts/orch/tsconfig.jsonasset · 289 bytesscripts/package.jsonruns · 445 bytesscripts/watch-pr/cli.test.tsruns · 6,167 bytesscripts/watch-pr/cli.tsruns · 6,989 bytesscripts/watch-pr/fakes.test-helper.tsruns · 3,357 bytesscripts/watch-pr/github.test.tsruns · 13,877 bytesscripts/watch-pr/github.tsruns · 25,533 bytesscripts/watch-pr/policy.test.tsruns · 12,417 bytesscripts/watch-pr/policy.tsruns · 25,201 bytesscripts/watch-pr/render.tsruns · 7,083 bytesscripts/watch-pr/runner.tsruns · 211 bytesscripts/watch-pr/tsconfig.jsonasset · 270 bytesscripts/watch-pr/types.compile.tsruns · 2,258 bytesscripts/watch-pr/types.tsruns · 12,649 bytesscripts/watch-pr/watch-prruns · 246 bytesscripts/worktree-audit.shruns · 3,915 bytes
Read excerpt
# Poteto mode
All delegation, lifecycle, isolation, history, connector, and capability behavior follows `references/codex-agent-runtime.md`. A playbook may narrow that contract but never broaden it.
## Codex session lifecycle
An explicit invocation must appear first after whitespace in the user prompt. Accept `$poteto-mode`, `$pstack-for-codex:poteto-mode`, or a Codex Markdown skill link with either exact label. The link must target a normalized absolute local path ending in `/skills/poteto-mode/SKILL.md`. This explicit invocation applies the complete skill on the activation turn. A trusted bundled hook records only session-scoped activation metadata for later turns. Casual mentions, quoted examples, and the words “poteto mode” do not activate it.
The exact phrase `disable $poteto-mode` opts the current session out. It removes only that session's state. Session end is advisory because Codex can resume the same session. State expires through the bundled versioned TTL collector instead.
The activation hook adds a `Poteto sticky receipt` context line when it ran successfully. If that receipt is absent, unknown, stale, or reports a mismatch, follow this skill for the current turn and state that cross-turn sticky behavior is inactive because trusted hooks could not be verified. Never infer global or cross-session activation.
Later active turns receive compact developer context from the hook. Compaction and resume use the same stable session state and must not duplicate the mode wrapper. Only the exact `pstack-poteto-agent` custom profile receives hook-provided subagent context. When that profile is unavailable, include `references/poteto-agent-prompt.md` in the generic delegate's task prompt. Generic delegates never inherit Poteto Mode merely because the parent session is active.