thincellerthinceller/claude-plugins/CLAUDE.md

claude-plugins

CLAUDE.md0 starsChanged 3 months agoMITView on GitHub

Claude Code plugins marketplace repository. Each plugin lives under plugins/<plugin-name>/ with its own plugin.json and skills. When adding a new plugin, register it in .claude-plugin/marketplace.json under the plugins array with name and source fields. Bump version in plugin.json when releasing changes to a plugin. Follow semver. evals/ contains headless behavior scenarios that verify plugin skills and hooks behave as intended (e.g. ambiguous requests get clarified instead of implemented). Run /verify-behavior after changes that affect plugin behavior. Each run spawns ~10…

In this repository2 other files it gives its agents.
- verify-behaviorSkill
- verifySkill

The file

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

3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
When adding a new plugin, register it in .claude-plugin/marketplace.json under the plugins array with name and source fields.
line 18
Very specific:
Use $ARGUMENTS in the body to accept user input
line 24
Distinctive:
Commit messages use HEREDOC with single-quoted delimiter to prevent variable expansion:
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

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Claude Code plugins marketplace repository. Each plugin lives under plugins/<plugin-name>/ with its own plugin.json and skills.

Plugin Structure

.claude-plugin/marketplace.json          # Marketplace metadata (plugin registry)
plugins/<name>/.claude-plugin/plugin.json # Plugin metadata (name, description, version, author)
plugins/<name>/skills/<skill>/SKILL.md    # Skill definition
plugins/<name>/skills/<skill>/references/ # Optional reference docs for a skill

When adding a new plugin, register it in .claude-plugin/marketplace.json under the plugins array with name and source fields.

Skill Development

SKILL.md frontmatter requires: name, description. Optional: argument-hint, disable-model-invocation.
description must include trigger phrases (e.g., Use when asked to "do X", "do Y")
Use $ARGUMENTS in the body to accept user input
For skills with side effects (deploy, destructive ops), set disable-model-invocation: true
Reference docs go in references/ subdirectory alongside SKILL.md

Git Conventions

Conventional commits: feat:, fix:, chore:, refactor:, docs:, style:, test:
Commit messages use HEREDOC with single-quoted delimiter to prevent variable expansion:
```
git commit -m "$(cat <<'EOF'
feat: add new skill
EOF
)"
```

Versioning

Bump version in plugin.json when releasing changes to a plugin. Follow semver.

Behavior Evals

evals/ contains headless behavior scenarios that verify plugin skills and hooks behave as intended (e.g. ambiguous requests get clarified instead of implemented). Run /verify-behavior after changes that affect plugin behavior. Each run spawns ~10 headless claude -p sessions and costs API tokens — do not run it for structural-only changes (use the verify skill for those).

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