skills
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
Read and follow CLAUDE.md in full before working in this repo. It is the shared source of truth for the architecture, project structure, skill format, eval-gated edit loop, commands, and gotchas. Do not maintain a divergent Codex copy of those rules. The per-skill index lives in skills/INDEX.md, linked from there. Codex-specific mapping: where shared guidance says AskUserQuestion, use Codex's structured user-input tool when available, otherwise ask one concise plain-text question. Skills under test are mirrored from the same source into…
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 31,774 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 repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- forge-buildSkill
- forge-debugSkill
- forge-design-exploreSkill
- forge-design-systemSkill
- forge-discoverySkill
- forge-docsSkill
- forge-dxSkill
- forge-hardenSkill
- forge-initSkill
- forge-planSkill
- forge-polishSkill
- forge-principlesSkill
- forge-retroSkill
- forge-reviewSkill
- forge-scopeSkill
- forge-shipSkill
- forgeSkill
- forge-wikiSkill
- lizardSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 3
Read and follow CLAUDE.md in full before working in this repo.
≈ “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.
Files
Skills Marketplace — Codex guidance
Read and follow CLAUDE.md in full before working in this repo. It
is the shared source of truth for the architecture, project structure, skill
format, eval-gated edit loop, commands, and gotchas. Do not maintain a divergent
Codex copy of those rules. The per-skill index lives in
skills/INDEX.md, linked from there.
Codex-specific mapping: where shared guidance says AskUserQuestion, use Codex's
structured user-input tool when available, otherwise ask one concise plain-text
question. Skills under test are mirrored from the same source into
.claude/skills/ and .codex/skills/; never fork their instructions by agent.
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.

