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.
npx agentmods add instructions/closedloop-ai/claude-plugins/claude-mdgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWhat 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.
| Model | Per session | Once 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 |
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.
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).
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.
- 2d ago First seen · 117 lines · 2,217 tokens per session scan A 93ea61a9c677
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.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
crystal CLAUDE.md
Instructions for stravu/crystal, covering crystal - multi-session claude code manager, project overview, references, implementation status: ✅ complete and ✅ implemented features.
agent-ship CLAUDE.md
Instructions for Agent-Ship/agent-ship, covering claude.md, project overview, commands, docker development (recommended) and local development (no docker).
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.