agentleFS
Sign inStart free
tim-mcdonnelltim-mcdonnell/skills/AGENTS.md

skills

AGENTS.md0 starsChanged 4 months agoMITView on GitHub

Public collection of agent skills: one folder per skill, <skill-name>/SKILL.md at the repo root. No bucket subdirectories; revisit only if the collection outgrows a flat list.

  • 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 31,700 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 repository3 other files it gives its agents.

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No bucket subdirectories; revisit only if the collection outgrows a flat list.

    line 4
  2. Very specific:

    Every skill ships agents/openai.yaml beside its SKILL.md, carrying interface.display_name and interface.short_description for the Codex …

    line 9
  3. Distinctive:

    Every skill has one linked entry in the README skill index, grouped by invocation mode.

    line 11

≈ “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

Skills repo

Public collection of agent skills: one folder per skill, <skill-name>/SKILL.md at the repo root. No bucket subdirectories; revisit only if the collection outgrows a flat list.

Invariants

  • Frontmatter requires name and description as strings, and name must match the folder name.
  • Every skill ships agents/openai.yaml beside its SKILL.md, carrying interface.display_name and interface.short_description for the Codex skill picker.
  • A user-invoked skill (disable-model-invocation: true) also sets policy.allow_implicit_invocation: false in its openai.yaml; a skill is user-invoked in both harnesses or neither.
  • Every skill has one linked entry in the README skill index, grouped by invocation mode; adding, renaming, or removing a skill updates the index in the same change.
  • CI runs node scripts/validate-skills.mjs on every push and pull request; run it locally before committing.
  • CLAUDE.md is a one-line shim pointing here; edit AGENTS.md, never CLAUDE.md.
  • Research notes live in docs/research/.
  • Skills stay generic for public consumption: no personal paths, model preferences, or private tooling.

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