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/lollipopkit/cc-plugins/claude-mdgit clone --depth 1 https://github.com/lollipopkit/cc-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 | $0.00511 | $0.00511 |
| Opus 5 | $0.00255 | $0.00255 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
cc-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 — 55 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.
Development Commands
Plugin Management
- Add local repository as marketplace:
/plugin marketplace add . - Add remote repository as marketplace:
/plugin marketplace add lollipopkit/cc-plugins - Install a plugin:
/plugin install <plugin-name>@lk-ccp - List installed plugins:
/plugin list
Linting & Formatting
- Markdown linting: Ensure compliance with
.markdownlint.json(disables MD013 and MD041). - No standard build or test commands exist at the root; development is done by testing plugins live in Claude Code.
Architecture & Code Structure
Project Overview
This repository is a monorepo for Claude Code plugins. Each plugin extends Claude's capabilities with specialized agents, commands, hooks, and skills.
Plugin Structure
All plugins follow a standard directory layout:
agents/: AI agent definitions (Markdown files with YAML frontmatter).commands/: Slash commands available in the CLI.hooks/: Lifecycle hooks (e.g.,Stophook defined inhooks.json).scripts/: Helper scripts (Bash/Python) used by commands or agents.skills/: Complex multi-step capabilities defined inSKILL.md.
Core Plugins
dev-loop: Automates the software development lifecycle (branch -> fix -> commit -> PR -> review).recursive-reasoning: Implements advanced reasoning patterns (Master/Sub-Agent, Tree of Thoughts, Reflexion).
Design Patterns
- Master/Sub-Agent: Used for complex orchestration. A "Master" agent plans and delegates to "Executor" sub-agents.
- Local Settings: Plugins often read per-project configuration from the target project's
.claude/<plugin-name>.local.mdfile. - Markdown-Driven Logic: Behavior is primarily defined via system prompts in Markdown files, using YAML frontmatter to specify tool permissions.
Coding Conventions
- GitHub CLI: Prefer using
ghfor all GitHub-related operations (PRs, issues, comments). - Git Protocol: Always create descriptive branches for new tasks.
- Verification: When implementing complex reasoning, always include a verification step to validate outputs.
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 · 55 lines · 511 tokens per session scan A b46105dd59dd
cc-plugins CLAUDE.md is an instructions file published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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 2026-08-31.
Other instructions, from other repositories
paperthin CLAUDE.md
Instructions for LilMGenius/paperthin, covering paperthin, philosophy, layout, skill.md format and disable-model-invocation: true ← user-invoked skills only.
rune CLAUDE.md
Instructions for Rune-kit/rune, covering rune — project configuration, tech stack, directory structure, mandatory skill routing and conventions.
agent-skills-toolkit AGENTS.md
Instructions for product-on-purpose/agent-skills-toolkit, covering agents.md - agent-skills-toolkit, what this project is, current state (read before assuming capabilities), conventions and build / test / lint.
agentx AGENTS.md
Instructions for agentsdance/agentx, covering agent rules and git operations.
agentx CLAUDE.md
Instructions for agentsdance/agentx, covering claude.md, build and run commands, build the binary (injects version from git tags), run the tui and run cli commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.