agentleFS
Sign inStart free
docxologydocxology/codomyrmex/.agents/AGENTS.md

codomyrmex

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

Repository-scoped, runtime-portable agent configuration: the canonical portable skill library shared by Codex, Claude Code, Hermes, and other runtimes. - skills/ — five portable skills (agent-interop, first-principles, mcp-tool-use, red-team, systems-thinking), each a folder with one SKILL.md. - README.md — human signpost listing each skill's purpose. - Codex discovers project skills directly from .agents/skills/. - Claude Code reaches them through thin pointer wrappers in .claude/skills/<name>/SKILL.md (for example .claude/skills/agent-interop/SKILL.md). - Hermes reads the tree as a read-only skills.external_dirs entry (example config). - Listed…

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:

    Keep runtime-specific settings (MCP servers, approvals) in each runtime's own file, such as .codex/config.toml, not in this tree.

    line 34

≈ “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 — codomyrmex/.agents

Purpose

Repository-scoped, runtime-portable agent configuration: the canonical portable skill library shared by Codex, Claude Code, Hermes, and other runtimes.

Key Files

  • skills/ — five portable skills (agent-interop, first-principles, mcp-tool-use, red-team, systems-thinking), each a folder with one SKILL.md.
  • README.md — human signpost listing each skill's purpose.

Dependencies

  • Codex discovers project skills directly from .agents/skills/.
  • Claude Code reaches them through thin pointer wrappers in .claude/skills/<name>/SKILL.md (for example .claude/skills/agent-interop/SKILL.md).
  • Hermes reads the tree as a read-only skills.external_dirs entry (example config).
  • Listed in .agent/SKILL_INDEX.md and described in docs/agents/agent-interoperability.md.
  • Parent: ../README.md · Root contract: ../AGENTS.md

Development Guidelines

  • This is the canonical copy for portable skills: edit workflow content here and keep runtime wrappers as pointers rather than forks.
  • Skills are referenced by name from .claude/skills/, .agent/SKILL_INDEX.md, and the interoperability doc — keep names stable, and update all of them together when a skill is added, renamed, or removed.
  • Keep runtime-specific settings (MCP servers, approvals) in each runtime's own file, such as .codex/config.toml, not in this tree.

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