agentleFS
TheophilusChinomonaTheophilusChinomona/idev/CLAUDE.md

idev

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

This repo IS the plugin (logic only — nothing here is mutable at runtime; per-project state lives in each project's .claude/idev/).

  • Commits and pushes

The file

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

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

  • 3

    Very specific

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

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

    Follow CONTRIBUTING.md: plugin=logic/project=state, generic-first (no stack- or project-specific rules stated as universal), honest …

    line 12
  2. Very specific:

    If a command documents a CLI flag, instinct-cli.py (or the relevant script) must actually implement it.

    line 27
  3. Very specific:

    Update ALL of: README counts + tables, CHANGELOG.md, version in BOTH .claude-plugin/plugin.json and .claude-plugin/marketplace.json (CI …

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

idev plugin — contributor guide

This repo IS the plugin (logic only — nothing here is mutable at runtime; per-project state lives in each project's .claude/idev/).

Before every commit

  • bash scripts/validate.sh — shell/python/JSON validation, stale-reference grep, skill-name↔dir consistency, plugin/marketplace version agreement, hook script existence, and the skill benchmark in --strict mode (every skill must score 10/10).
  • python3 -m pytest tests/ — keep all tests green.
  • Follow CONTRIBUTING.md: plugin=logic/project=state, generic-first (no stack- or project-specific rules stated as universal), honest capabilities (never document behavior the runtime doesn't deliver, no phantom commands or flags), token-frugal (SKILL.md target < 250 lines).

Wiring rules (things that silently break)

  • Frontmatter: skills = name + description (+ allowed-tools/ argument-hint); agents = name, description, tools (comma-separated string), model; commands = description + argument-hint. Anything else is silently ignored — don't add it.
  • Skill descriptions need "Use when..." trigger phrasing (benchmark check).
  • ${CLAUDE_PLUGIN_ROOT} expands ONLY in this repo's hooks/hooks.json — never tell users to put it in their settings.json.
  • Optional hooks (observer, compact) are pre-registered in hooks/hooks.json but flag-guarded; toggles live in /idev:hooks (commands/hooks.md).
  • If a command documents a CLI flag, instinct-cli.py (or the relevant script) must actually implement it.

Adding/removing components

Update ALL of: README counts + tables, CHANGELOG.md, version in BOTH .claude-plugin/plugin.json and .claude-plugin/marketplace.json (CI enforces agreement), and templates/claude-md-snippet.md if the workflow chain or delegation map changed. Third-party adaptations keep MIT attribution in-file, in the README, and in the changelog.

Releases

Tag vX.Y.Z matching plugin.json, push with --follow-tags, gh release create. Branch protection on master requires the validate check for PRs; admin direct pushes bypass it but CI still runs post-push — check 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.

Reviews can't be read right now.

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.