agentleFS
kadeskikadeski/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 3 days agoMITView on GitHub

The repo is a marketplace, kadeski. Each plugin is a folder plugins/<plugin>/ that ships on its own and is listed on its own in the Claude plugin directory. A plugin holds its skills in skills/<name>/SKILL.md, a README.md (its user doc and directory listing, at least 40 words) and a LICENSE. Keep anything that does not ship, such as evals, tests and scripts, out of plugins/: a plugin's tests live in tests/<plugin>/. A plugin may live in its own repository instead:…

  • 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 33,315 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 repository2 other files it gives its agents.

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before committing, run scripts/check.sh.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 42,283 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

AGENTS.md

The repo is a marketplace, kadeski. Each plugin is a folder plugins/<plugin>/ that ships on its own and is listed on its own in the Claude plugin directory. A plugin holds its skills in skills/<name>/SKILL.md, a README.md (its user doc and directory listing, at least 40 words) and a LICENSE. Keep anything that does not ship, such as evals, tests and scripts, out of plugins/: a plugin's tests live in tests/<plugin>/.

A plugin may live in its own repository instead: study is in kadeski/study, and its marketplace entry is a url source with that repository's https:// address and its release branch. The directory follows a hook's Python script only at a repository root, which is why it moved. Use url with https:// rather than a github source: claude plugin update clones a github source over SSH, which fails where github.com is not in known_hosts.

Each plugin has one manifest, .claude-plugin/plugin.json (Grok Build reads it too), and is listed in one marketplace, .claude-plugin/marketplace.json (Grok Build and npx skills read it too). The plugins ship for Claude Code only. A plugin may leave version out of its manifest (sdlc does): each commit then counts as a release, so accounts that sync the marketplace pick up every push. Gemini CLI has no plugin manifest: users install a skill with gemini skills install <repo url> --path plugins/<plugin>/skills/<name>.

To add a plugin, create its folder, add it to the marketplace and to the list in README.md.

Before committing, run scripts/check.sh.

Eval cases for a skill live in evals/<skill>/; see evals/README.md. /hillclimb <skill> improves a skill against them.

Writing style for skills and docs: simple terms, plain dashes (never em dashes), no filler.

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.