agentleFS
jscraikjscraik/Agent-Skills/Plugins/AGENTS.md

Agent-Skills / Plugins

AGENTS.md9 starsChanged 46 days agoApache-2.0View on GitHub

- Treat uppercase Plugins/** as canonical plugin-owned source unless a nested guide or manifest explicitly marks a path as generated output. - Keep plugin behavior in canonical plugin source, bundled hooks, and related Infrastructure/** contracts. Do not move product behavior into lowercase runtime/cache mirrors. - On case-insensitive filesystems, be careful with plugins and Plugins path collisions. Verify the real path before moving, deleting, or syncing. - Use plugin install, status, and sync commands from the root ./bin/ask surface when changing…

The file

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

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Treat uppercase Plugins/ as canonical plugin-owned source unless a nested guide or manifest explicitly marks a path as generated output.

    line 14
  2. Very specific:

    Keep plugin behavior in canonical plugin source, bundled hooks, and related Infrastructure/ contracts.

    line 16
  3. Very specific:

    Use plugin install, status, and sync commands from the root ./bin/ask surface when changing runtime readiness.

    line 21
  4. Very specific:

    Only command hooks are currently executable in the plugin runtime.

    line 37
  5. Distinctive:

    Before editing, prove whether the target is canonical source, generated tracked output, runtime cache, or local state.

    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

Plugins Agent Guide

Scope

  • Applies to uppercase Plugins/**.
  • Inherits the repository root AGENTS.md.

Edit Policy

  • Treat uppercase Plugins/** as canonical plugin-owned source unless a nested guide or manifest explicitly marks a path as generated output.
  • Keep plugin behavior in canonical plugin source, bundled hooks, and related Infrastructure/** contracts. Do not move product behavior into lowercase runtime/cache mirrors.
  • On case-insensitive filesystems, be careful with plugins and Plugins path collisions. Verify the real path before moving, deleting, or syncing.
  • Use plugin install, status, and sync commands from the root ./bin/ask surface when changing runtime readiness.

Context Pointers

  • Plugin readiness rules: ../Docs/agents/17-skill-management.md#plugin-desktop-readiness.
  • Skill Factory lifecycle and routing: ../Plugins/skill-factory/README.md.
  • Path ownership: ../Docs/agents/14-path-ownership-boundaries.md.
  • Repository vocabulary: ../UBIQUITOUS_LANGUAGE.md.

For plugin creation, hardening, or hook changes, apply the plugin-factory:plugin-builder contract and run its plugin_builder.pyw validate gate before handoff. Bundled hooks belong at hooks/hooks.json and are declared from plugin.json as ./hooks/hooks.json; use a top-level hooks object with matcher-level hooks arrays, command-hook timeout in seconds, and ${PLUGIN_ROOT} or ${PLUGIN_DATA} for plugin-owned commands. Only command hooks are currently executable in the plugin runtime; prompt, agent, and async hook forms are parsed but not runtime-supported. Enable plugin_hooks alongside plugins and hooks before relying on bundled hooks.

Validation

  • Before editing, prove whether the target is canonical source, generated tracked output, runtime cache, or local state.
  • For plugin readiness claims, use the repository plugin status contract rather than filesystem presence alone.

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.