agentleFS
Sign inStart free
carlkiblercarlkibler/agent-skills/AGENTS.md

agent-skills

AGENTS.md6 starsChanged 4 months agoMITView on GitHub

Compatibility shim pointing to CLAUDE.md. Source of truth for multi-agent skill conventions.

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every skill and script must work across agents, not just Claude:

    line 17
  2. Distinctive:

    Skill instructions: must be written in plain language, not Claude-specific syntax

    line 19
  3. Very specific:

    Scripts: must be standalone (PEP 723 headers, try/except ImportError fallbacks) — no agent-specific tooling required to run them

    line 20
  4. Very specific:

    Run python3 scripts/sync_codex_packaging.py after any skill changes to keep Codex packaging current

    line 22
  5. Very specific:

    Use ${CLAUDE_SKILL_DIR} (or the agent-equivalent env var) to reference bundled files at runtime

    line 38

≈ “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

Source of truth: CLAUDE.md This file is a thin compatibility shim. All conventions, structure, and requirements live in CLAUDE.md. Read that first.

What This Repo Is

A shared skill collection designed to work across multiple AI coding agents — Claude Code, Codex, Copilot, Gemini CLI, and any agent that follows the Agent Skills open standard. Skills are agent-agnostic by design.

Multi-Agent Support Is Required

Every skill and script must work across agents, not just Claude:

  • Skill instructions must be written in plain language, not Claude-specific syntax
  • Scripts must be standalone (PEP 723 headers, try/except ImportError fallbacks) — no agent-specific tooling required to run them
  • Distribution uses both Claude Code marketplace (.claude-plugin/) and Codex plugin packaging (.agents/, plugins/) — both must stay in sync
  • Run python3 scripts/sync_codex_packaging.py after any skill changes to keep Codex packaging current

Tool Name Mapping

Skills use Claude Code tool names in their instructions. Other agents should consult their platform's mapping:

  • Codex: references/codex-tools.md
  • Copilot CLI: references/copilot-tools.md
  • Gemini CLI: tool mapping is loaded automatically via GEMINI.md

Creating or Modifying Skills

See CLAUDE.md for full conventions. Short version:

  1. Skill lives in skills/<name>/SKILL.md with YAML frontmatter (name, description required)
  2. Scripts go in skills/<name>/scripts/ — standalone, PEP 723, works without any agent
  3. Register in .claude-plugin/marketplace.json for Claude, then run the sync script for Codex
  4. Use ${CLAUDE_SKILL_DIR} (or the agent-equivalent env var) to reference bundled files at runtime

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