agentleFS
Sign inStart free
docxologydocxology/codomyrmex/.agents/skills/agent-interop/AGENTS.md

codomyrmex / agent-interop

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

Portable repository-scoped skill: Keep Codex, Claude Code, and Hermes workflows aligned through portable skills, explicit runtime adapters, and shared MCP contracts. Defined entirely by SKILL.md. - SKILL.md — canonical definition: frontmatter (name: agent-interop, description), where each runtime discovers skills and MCP settings, and the handoff record fields (objective, scope, assumptions, files changed, tool calls, evidence, unresolved risks, next verification step). - README.md — human signpost. - Claude Code wrapper: .claude/skills/agent-interop/SKILL.md only points back to this file. - Runtime files it…

The file

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

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Treat .agents/skills/ as the portable, repository-scoped skill library.

    line 32
  2. Distinctive:

    When a runtime changes where it reads skills or MCP settings, update this file and the "Runtime setup" section of the interoperability doc …

    line 36
  3. Distinctive:

    Do not encode one runtime's permission model as if another runtime honors it.

    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 — codomyrmex/.agents/skills/agent-interop

Purpose

Portable repository-scoped skill: Keep Codex, Claude Code, and Hermes workflows aligned through portable skills, explicit runtime adapters, and shared MCP contracts. Defined entirely by SKILL.md.

Key Files

  • SKILL.md — canonical definition: frontmatter (name: agent-interop, description), where each runtime discovers skills and MCP settings, and the handoff record fields (objective, scope, assumptions, files changed, tool calls, evidence, unresolved risks, next verification step).
  • README.md — human signpost.

Dependencies

  • Claude Code wrapper: .claude/skills/agent-interop/SKILL.md only points back to this file.
  • Runtime files it names: .codex/config.toml (Codex MCP), a project .mcp.json for Claude Code (opt-in from config/claude_code_mcp.example.json), and ~/.hermes/config.yaml (from config/hermes_external_skills.example.yaml).
  • Final step of the composition order in docs/agents/agent-interoperability.md.
  • Parent: ../AGENTS.md

Development Guidelines

  • Treat .agents/skills/ as the portable, repository-scoped skill library; mirror into runtime-specific folders rather than forking content.
  • This is the canonical copy; runtime wrappers such as .claude/skills/agent-interop/ stay pointers — change the workflow here.
  • When a runtime changes where it reads skills or MCP settings, update this file and the "Runtime setup" section of the interoperability doc together.
  • Do not encode one runtime's permission model as if another runtime honors it.

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