agentleFS
Sign inStart free
jukrapjukrap/ai-agent-playbook/AGENTS.md

ai-agent-playbook

AGENTS.md2 starsChanged 4 months agoMITView on GitHub

This repository contains reusable AI agent skills and project templates. Keep content agent-agnostic unless it belongs under adapters/. Run these after edits: If local installed copies need updating, run:

  • 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 repository7 other files it gives its agents.

The file

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

11 rules. About 1 is common, 4 are distinctive, and 6 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Before adding, moving, or renaming content, read docs/maintenance.md.

    line 7
  2. Very specific:

    Keep skills/*/*/SKILL.md concise and trigger-focused.

    line 8
  3. Very specific:

    Put longer reusable details in references/.

    line 9
  4. Very specific:

    Keep project-copyable root policies under templates/agents.

    line 10
  5. Very specific:

    Keep copyable project-memory docs under templates/project-playbook.

    line 11
  6. Common:

    Do not put personal absolute paths, company names, credentials, internal URLs, branch names, or PR numbers in public docs.

    line 12
  7. Distinctive:

    Update Korean translations in the same change as English source edits.

    line 13
  8. Distinctive:

    Use lowercase hyphenated skill names.

    line 20
  9. Very specific:

    Prefer one-level references from SKILL.md.

    line 23
  10. Distinctive:

    Run these after edits:

    line 27
  11. Distinctive:

    If local installed copies need updating, run:

    line 35

≈ “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

This repository contains reusable AI agent skills and project templates. Keep content agent-agnostic unless it belongs under adapters/.

Working rules

  • Before adding, moving, or renaming content, read docs/maintenance.md.
  • Keep skills/*/*/SKILL.md concise and trigger-focused.
  • Put longer reusable details in references/.
  • Keep project-copyable root policies under templates/agents.
  • Keep copyable project-memory docs under templates/project-playbook.
  • Do not put personal absolute paths, company names, credentials, internal URLs, branch names, or PR numbers in public docs.
  • Update Korean translations in the same change as English source edits.
  • Validate skills and translations after editing.
  • Sync installed local copies only from this repository.
  • For commits and PRs, use Conventional Commit type/scope, write the subject/body in the user's or repository's working language, and include a body plus verification notes for non-trivial changes.

Skill structure

  • Use lowercase hyphenated skill names.
  • SKILL.md frontmatter must contain only name and description.
  • Description starts with Use when... and describes trigger conditions, not the workflow.
  • Prefer one-level references from SKILL.md.

Verification

Run these after edits:

.\scripts\validate-skills.ps1
.\scripts\validate-translations.ps1
.\scripts\sync-skills.ps1 -WhatIf

If local installed copies need updating, run:

.\scripts\sync-skills.ps1

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