agentleFS
Sign inStart free
MbappeWUMbappeWU/murder-board/AGENTS.md

murder-board

AGENTS.md15 starsChanged 49 days agoMITView on GitHub

Installing these skills for a user? Follow INSTALL.md instead of this file. This file is for agents that are editing this repository. Then update the matching portable/zh-CN/<name>.md so the Chinese version says the same thing. When releasing, bump metadata.version in every skill and version in both .claude-plugin/*.json together; the validator checks that they match.

  • 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 repository5 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, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Installing these skills for a user?: Follow INSTALL.md instead of this file.

    line 3
  2. Very specific:

    When releasing, bump metadata.version in every skill and version in both .claude-plugin/*.json together.

    line 25
  3. Very specific:

    Every skill mirrors the user's language, never invents facts about the user's world, and uses [placeholders] for facts it doesn't have.

    line 30

≈ “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

AGENTS.md

Installing these skills for a user? Follow INSTALL.md instead of this file.

This file is for agents that are editing this repository.

Layout

  • skills/<name>/SKILL.md: the skills, in the open Agent Skills format. Frontmatter: name (matches the folder), description (≤ 1024 characters, no : sequences, says what the skill does and when to trigger it, including Chinese trigger phrases), license, metadata.version.
  • skills/<name>/references/: detail loaded on demand. Keep each SKILL.md body under 500 lines.
  • portable/en/: generated single-file prompts for chat apps. Never edit by hand.
  • portable/zh-CN/: hand-maintained Chinese versions of the portable prompts.
  • site/index.html: the GitHub Pages template. scripts/build-site.mjs injects the portable prompts and writes the site to _site/ (not committed).
  • .claude-plugin/: Claude Code plugin and marketplace manifests.

After changing a skill

node scripts/build-portable.mjs   # regenerate portable/en
node scripts/validate.mjs         # must pass; CI runs the same check

Then update the matching portable/zh-CN/<name>.md so the Chinese version says the same thing.

When releasing, bump metadata.version in every skill and version in both .claude-plugin/*.json together; the validator checks that they match.

Writing style for skills

  • Imperative, specific and short. Tell the model exactly what to output and in what shape.
  • Every skill mirrors the user's language, never invents facts about the user's world, and uses [placeholders] for facts it doesn't have.
  • Hard on the argument, never on the person.

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