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

codomyrmex / skills

AGENTS.md10 starsChanged 38 days agoMITView on GitHub

The canonical, repository-scoped portable skill library. Runtime wrappers (for example .claude/skills/<name>/SKILL.md) point back to these definitions instead of copying them. One folder per skill, each with a single SKILL.md plus a README.md/AGENTS.md pair: - agent-interop/ — keep Codex, Claude Code, and Hermes aligned through portable skills and shared MCP contracts. - first-principles/ — reduce an ambiguous problem to verified facts, constraints, and explicit decisions. - mcp-tool-use/ — schema inspection, least-privilege selection, approvals, and verified results for MCP calls. - red-team/…

The file

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

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

  • 2

    Very specific

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

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

    Keep skill frontmatter (name, description) stable — runtimes index by it.

    line 38
  2. Very specific:

    Follow the portable Agent Skills layout: concise frontmatter, one SKILL.md, supporting files only when a skill needs them.

    line 43

≈ “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

Purpose

The canonical, repository-scoped portable skill library. Runtime wrappers (for example .claude/skills/<name>/SKILL.md) point back to these definitions instead of copying them.

Key Files

One folder per skill, each with a single SKILL.md plus a README.md/AGENTS.md pair:

  • agent-interop/ — keep Codex, Claude Code, and Hermes aligned through portable skills and shared MCP contracts.
  • first-principles/ — reduce an ambiguous problem to verified facts, constraints, and explicit decisions.
  • mcp-tool-use/ — schema inspection, least-privilege selection, approvals, and verified results for MCP calls.
  • red-team/ — adversarial review of realistic failure and abuse paths within authorized scope.
  • systems-thinking/ — map boundaries, dependencies, feedback loops, and leverage points.
  • README.md — human signpost.

Dependencies

  • Discovery: Codex reads this directory directly; Claude Code uses the wrappers in .claude/skills/; Hermes lists it under skills.external_dirs (example).
  • Composition order for a substantial change (first-principles -> systems-thinking -> red-team -> mcp-tool-use -> agent-interop) is defined in docs/agents/agent-interoperability.md.
  • Indexed in .agent/SKILL_INDEX.md.
  • Parent: ../AGENTS.md

Development Guidelines

  • Keep skill frontmatter (name, description) stable — runtimes index by it; name must match the folder name.
  • New skills must be added to the crossover index (.agent/SKILL_INDEX.md), the skill table in the interoperability doc, and a .claude/skills/<name>/ pointer wrapper.
  • Follow the portable Agent Skills layout: concise frontmatter, one SKILL.md, supporting files only when a skill needs them.

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