chrysogonuschrysogonus/power-agents/AGENTS.md

power-agents

AGENTS.md4 starsChanged 6 days agoMITView on GitHub

This repository's core is the verify gate (hooks/verify-gate.py), installed for Codex and Claude Code. Instructions, skills, status lines, Codex rules, and Claude Code guards are optional components selected with ./install.sh --components. - Keep a gate-only install working: it must not need tomlkit, PyYAML, or Node.js, and must not create or change files that belong to optional components. - Edit files in this repository, not their installed copies under ~/.agents or the configured Codex and Claude roots. - Keep cross-project instructions…

Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository28 other files it gives its agents.
- skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- agent-browserSkill
- break-uiSkill
- claude-skill-creatorSkill
- codebase-designSkill
- code-simplificationSkill
- design-taste-frontendSkill
- domain-modelingSkill
- finishing-a-development-branchSkill
- frontend-designSkill
- grillingSkill
- handoffSkill
- improve-codebase-architectureSkill
- performance-optimizationSkill
- ponytailSkill
- prompt-refinerSkill
- readme-syncSkill
- review-reportSkill
- security-best-practicesSkill
- supabase-postgres-best-practicesSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- triageSkill
- using-git-worktreesSkill
- vercel-composition-patternsSkill
- vercel-react-best-practicesSkill
- writing-for-agentsSkill

The file

We split this AGENTS.md into the rules it gives an agent

7 rules. About 0 are common, 0 are distinctive, and 7 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Keep a gate-only install working: it must not need tomlkit, PyYAML, or Node.js, and must not create or change files that belong to optional …
line 8
Very specific:
Keep cross-project instructions in instructions/general-global.md.
line 13
Very specific:
Put each skill in skills/<name>/SKILL.md.
line 14
Very specific:
Keep authored Codex rules in policies/codex/shared.rules.
line 16
Very specific:
Keep agent-specific settings under settings/<agent>/.
line 18
Very specific:
Run ./install.sh after configuration changes.
line 19
Very specific:
Run ./scripts/check.sh before finishing changes.
line 21

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

Project Instructions

This repository's core is the verify gate (hooks/verify-gate.py), installed for Codex and Claude Code. Instructions, skills, status lines, Codex rules, and Claude Code guards are optional components selected with ./install.sh --components.

Keep a gate-only install working: it must not need tomlkit, PyYAML, or Node.js, and must not create or change files that belong to optional components.
Edit files in this repository, not their installed copies under ~/.agents or the configured Codex and Claude roots.
Keep cross-project instructions in instructions/general-global.md.
Put each skill in skills/<name>/SKILL.md; its frontmatter name must match the directory name.
Keep authored Codex rules in policies/codex/shared.rules; interactive rules remain in the application-managed Codex root.
Keep agent-specific settings under settings/<agent>/.
Run ./install.sh after configuration changes. It must remain idempotent and preserve supported unmanaged values as documented in docs/installation.md.
Run ./scripts/check.sh before finishing changes. It includes Bash syntax and static analysis for every shell script, isolated behavioral tests, and git diff --check coverage.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free