claude-plugins CLAUDE.md

Repository instructions for a collection of Claude Code plugins, which are add-ons that extend an AI coding assistant. The repository is a monorepo, meaning several related projects are kept and tested together in one code repository.

In plain words
What is it for?
Use it when setting up the project, running tests, linting Python or TypeScript code, checking types, or changing one of its plugins.
Why use it?
It gives the coding assistant the commands, folder structure, setup steps, and checks needed to work correctly in this repository.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/closedloop-ai/claude-plugins/claude-md
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 2,217 This file is loaded in full into every session.
When invoked 2,217 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02217 $0.02217
Opus 5 $0.01108 $0.01108
Sonnet 5 $0.00443 $0.00443
Haiku 4.5 $0.00222 $0.00222

Measured 2d ago against content hash 93ea61a9c677, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-plugins CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

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

What This Is

A monorepo of open-source Claude Code plugins by ClosedLoop. Six plugins — bootstrap, code, code-review, judges, platform, self-learning — each under plugins/<name>/ with a standard layout: .claude-plugin/plugin.json, agents/, commands/, skills/, hooks/, tools/python/, scripts/.

Commands

# Setup
python3.13 -m venv .venv && source .venv/bin/activate
pip install ruff pyright pytest
git config core.hooksPath .githooks

# Testing
pytest plugins/                          # all tests
pytest plugins/code/tools/python/        # single plugin's tests
pytest plugins/code/tools/python/test_count_tokens.py -k test_name  # single test

# Linting & type checking (match CI exactly — local-pyright vs uv-run-pyright
# divergence can mask reportOptionalMemberAccess and similar diagnostics)
uv run ruff check .
uv run pyright

# TypeScript tool scripts (toolchain lives at tools/design-inventory; bundles committed into plugin)
cd tools/design-inventory
npm ci             # once
npm test           # vitest
npm run typecheck  # tsc --noEmit
npm run build      # rebuild committed dist/*.mjs (written to plugins/code/skills/design-inventory/scripts/dist/)

Architecture

Plugin Structure

Each plugin's manifest lives at plugins/<name>/.claude-plugin/plugin.json with name, description, version, and author fields. The .claude-plugin/marketplace.json at repo root registers all six plugins.

Agent Definitions

Markdown files with YAML frontmatter specifying name, description, model, tools, and skills. Model selection convention: opus for creative/planning, sonnet for implementation, haiku for lightweight coordination. Only reference tools listed in frontmatter — no hallucinated tool calls.

Skill Identifiers

Always use plugin-name:skill-name format (e.g., self-learning:learning-quality, not learning-quality).

Read the full file on GitHub · 117 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 117 lines · 2,217 tokens per session scan A 93ea61a9c677

Subscribe to this mod's changes

claude-plugins CLAUDE.md is an instructions file published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,217 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.