agentleFS
Sign inStart free
AkashPriyadarshiiAkashPriyadarshii/cookbook/AGENTS.md

cookbook

AGENTS.md0 starsChanged 3 months agoMITView on GitHub

For any AI agent asked to create or update a skill here. 1. Check before writing. Read the target skill file first. Update > duplicate. If the lesson exists, sharpen it; don't add a second copy. 2. Every lesson cites its bug. One line: what actually broke. No lesson without a scar. "Best practice" without a failure story belongs in a style guide, not here. 3. Thin or nothing. ≤100 lines per SKILL.md. If it exceeds that, split by topic…

The file

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

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Check before writing: Read the target skill file first.

    line 5
  2. Distinctive:

    If the lesson exists, sharpen it.

    line 6
  3. Distinctive:

    Only capture what docs get wrong or omit: boundary behavior, silent failures, cross-compilation traps, concurrency footguns.

    line 13
  4. Distinctive:

    Delete stale content: If a newer toolchain invalidates a lesson, remove it in the same edit that adds new ones.

    line 15

≈ “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 — cookbook contribution rules

For any AI agent asked to create or update a skill here.

  1. Check before writing. Read the target skill file first. Update > duplicate. If the lesson exists, sharpen it; don't add a second copy.
  2. Every lesson cites its bug. One line: what actually broke. No lesson without a scar. "Best practice" without a failure story belongs in a style guide, not here.
  3. Thin or nothing. ≤100 lines per SKILL.md. If it exceeds that, split by topic (rust/, rust-ffi/) and delete overlap.
  4. Don't duplicate official docs. Idioms, syntax, stdlib reference → skip. Only capture what docs get wrong or omit: boundary behavior, silent failures, cross-compilation traps, concurrency footguns.
  5. Delete stale content. If a newer toolchain invalidates a lesson, remove it in the same edit that adds new ones. Note the version where relevant.
  6. Polyglot topics (git, CI, JNI boundaries spanning two languages, build systems) go in cross/.
  7. Format: frontmatter with name + description (when-to-use trigger), then lessons as ## N. Title with bug → fix → check pattern.

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