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.
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 32,671 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 repository80 other files it gives its agents.
- accessibility-audit-websitesSkill
- accessibility-performance-polishSkill
- agent-evaluation-operationsSkill
- agent-memory-provenanceSkill
- agent-orchestration-architectureSkill
- animation-easing-languageSkill
- animation-jank-qaSkill
- animation-tool-routerSkill
- anti-generic-website-reviewSkill
- brand-voice-to-ui-copySkill
- browser-inspection-workflowSkill
- code-change-safety-checkpointSkill
- code-change-undo-revertSkill
- color-material-lighting-directionSkill
- content-pruning-reviewSkill
- content-structure-information-architectureSkill
- conversion-forms-checkout-polishSkill
- creativitySkill
- critical-thinkingSkill
- cross-browser-qaSkill
- css-grid-editorial-systemsSkill
- cta-language-systemsSkill
- deep-researchSkill
- design-motion-principlesSkill
- editorial-typography-systemsSkill
- evidence-reconciliationSkill
- final-client-handoffSkill
- frontend-quality-auditorSkill
- frontend-tooling-trust-gateSkill
- gsap-performanceSkill
- hero-image-art-directionSkill
- image-crop-responsive-qaSkill
- image-video-loading-qaSkill
- logical-thinkingSkill
- mobile-responsive-qaSkill
- modern-site-engineeringSkill
- motion-language-directorSkill
- motion-performance-qaSkill
- motion-react-layout-transitionsSkill
- motion-react-microinteractionsSkill
- motion-react-page-transitionsSkill
- motion-react-patternsSkill
- nextjs-app-router-routingSkill
- nextjs-server-client-boundariesSkill
- nextjs-site-architectureSkill
- non-generic-web-copySkill
- performance-audit-websitesSkill
- performance-budget-labSkill
- premium-visual-reference-librarySkill
- premium-web-build-gateSkill
- radix-accessible-primitivesSkill
- react-accessible-componentsSkill
- react-component-compositionSkill
- react-component-craftSkill
- react-error-loading-empty-statesSkill
- react-form-patternsSkill
- react-responsive-componentsSkill
- react-state-and-effects-disciplineSkill
- reduced-motion-designSkill
- responsive-visual-polish-qaSkill
- The first 60 shown.
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
- Distinctive: line 7
Before a release or pull request that changes skills, collections, scripts, docs, or workflows, run:
- Distinctive: line 25
Never invent users, forks, issues, benchmark results, testimonials, or adoption claims.
- Distinctive: line 27
Do not present fictional values inside a demo mockup as repository telemetry.
- Distinctive: line 28
Treat browser, accessibility, performance, and security checks as unperformed until they actually run.
- Distinctive: line 33
Keep installer behavior explicit and preserve dry-run and backup-on-replace safeguards.
- Common: line 34
Do not add secrets, private paths, credentials, generated caches, or machine-specific state.
- Distinctive: line 35
Before public commits, verify the repository author/committer identity is suitable for publication.
- Distinctive: line 36
Prefer focused changes that improve usefulness, safety, reproducibility, or documentation.
≈ “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.
Files
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 --checkRegenerate 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.
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
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.

