agentleFS
TheGoat395TheGoat395/Codex-Skills/AGENTS.md

Codex-Skills

AGENTS.md136 starsChanged 5 months agoMITView on GitHub

Codex-Skills is a public, Codex-first Agent Skills library. Keep the public core curated, installable, inspectable, and honest about evidence. Before a release or pull request that changes skills, collections, scripts, docs, or workflows, run: Regenerate manifest.json and SKILL_INVENTORY.md when skill folders change.

The file

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

8 rules. About 1 is common, 7 are distinctive, and 0 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Before a release or pull request that changes skills, collections, scripts, docs, or workflows, run:

    line 7
  2. Distinctive:

    Never invent users, forks, issues, benchmark results, testimonials, or adoption claims.

    line 25
  3. Distinctive:

    Do not present fictional values inside a demo mockup as repository telemetry.

    line 27
  4. Distinctive:

    Treat browser, accessibility, performance, and security checks as unperformed until they actually run.

    line 28
  5. Distinctive:

    Keep installer behavior explicit and preserve dry-run and backup-on-replace safeguards.

    line 33
  6. Common:

    Do not add secrets, private paths, credentials, generated caches, or machine-specific state.

    line 34
  7. Distinctive:

    Before public commits, verify the repository author/committer identity is suitable for publication.

    line 35
  8. Distinctive:

    Prefer focused changes that improve usefulness, safety, reproducibility, or documentation.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Repository Operating Notes

Codex-Skills is a public, Codex-first Agent Skills library. Keep the public core curated, installable, inspectable, and honest about evidence.

Required Checks

Before a release or pull request that changes skills, collections, scripts, docs, or workflows, run:

python3 scripts/validate_skills.py
python3 scripts/validate_public_package.py
python3 scripts/test_catalog.py
python3 scripts/test_skill_helpers.py
python3 scripts/install_skills.py --list-collections
python3 scripts/install_skills.py --dry-run
python3 -m py_compile scripts/*.py
git diff --check

Regenerate manifest.json and SKILL_INVENTORY.md when skill folders change.

Evidence Rules

  • Label measured results, estimates, owner-only GitHub metrics, and derived calculations separately.
  • Never invent users, forks, issues, benchmark results, testimonials, or adoption claims.
  • Preserve the exact prompt, outputs, commands, and limitations for paired benchmarks.
  • Do not present fictional values inside a demo mockup as repository telemetry.
  • Treat browser, accessibility, performance, and security checks as unperformed until they actually run.

Change Hygiene

  • Inspect the worktree before editing and use a branch for risky changes.
  • Keep installer behavior explicit and preserve dry-run and backup-on-replace safeguards.
  • Do not add secrets, private paths, credentials, generated caches, or machine-specific state.
  • Before public commits, verify the repository author/committer identity is suitable for publication; do not rely on an automatically inferred machine address.
  • Prefer focused changes that improve usefulness, safety, reproducibility, or documentation.

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.