What is cc-plugins CLAUDE.md?

A repository guide for developing and validating plugins for Claude Code, an AI coding tool. It documents the project structure, marketplace registry, required files, and automated checks.

Use it when adding or changing marketplace plugins, checking plugin files locally, and understanding the validation and review workflow.

It gives contributors one place to learn the repository rules and avoid invalid plugin metadata, missing files, or duplicate names.

cc-plugins CLAUDE.md — Instructions file by kossakovsky

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/kossakovsky/cc-plugins/claude-md

Clone the repo

git clone --depth 1 https://github.com/kossakovsky/cc-plugins

Per session 827 This file is loaded in full into every session.

When invoked 827 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.

Model	Per session	Once invoked
Fable 5	$0.00827	$0.00827
Opus 5	$0.00413	$0.00413
Sonnet 5	$0.00165	$0.00165
Haiku 4.5	$0.00083	$0.00083

Measured 2d ago against content hash 4389150cda62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 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.

Project Overview

Community marketplace of plugins for Claude Code. Plugins are installed via:

/plugin marketplace add kossakovsky/cc-plugins
/plugin install <plugin-name>@cc-plugins

Validation

CI runs on push to main/develop and on PRs to main (.github/workflows/validate-plugins.yml):

Validates marketplace.json structure and required fields
Validates each plugin's plugin.json (valid JSON, required fields, kebab-case name)
Checks for duplicate plugin names
Verifies plugin directories and README.md exist

Local validation for plugin development:

/plugin-development:validate

Note: plugins/plugin-development/scripts/validate-plugin.sh is a hook script invoked automatically on Write/Edit — it cannot be run standalone.

PR review is automated via Claude Code GitHub App (auto-reviews all PRs using instructions below).

Architecture

Marketplace Registry

.claude-plugin/marketplace.json — central registry listing all plugins. Each entry requires: name, source (relative path like ./plugins/<name>), description, version. Optional: author.name, category, tags, keywords.

Plugin Structure

Each plugin lives in plugins/<name>/ and must contain:

.claude-plugin/plugin.json — manifest with required fields: name (kebab-case), version, description
README.md — documentation

Optional component directories:

commands/ — slash commands as .md files with YAML frontmatter (description field recommended)
skills/ — skill definitions
agents/ — sub-agent definitions as .md files
hooks/ — hooks configuration (hooks.json)

Current Plugins

Plugin	Purpose
`switch-provider`	Switch Claude Code between AI providers (Anthropic, Z.AI, Kimi, MiniMax) with a single command
`plugin-development`	Scaffold, validate, review, and submit Claude Code plugins
`commit`	Smart git commits with conventional commit message generation
`writing-skills`	Create, test, and bulletproof skills using TDD methodology

Read the full file on GitHub · 93 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.

2d ago First seen · 93 lines · 827 tokens per session scan A 4389150cda62

Subscribe to this mod's changes

cc-plugins CLAUDE.md is an instructions file published in the GitHub repository kossakovsky/cc-plugins (3 stars, last pushed 5mo ago), licensed MIT. It adds 827 tokens to every session, about $0.0041 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.

Building agents

cc-plugins CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Project Overview

Validation

Architecture

Marketplace Registry

Plugin Structure

Current Plugins

What this file has done since we first saw it

Other instructions, from other repositories

spellbook AGENTS.md

open-supermarkets AGENTS.md

helm copilot-instructions.md

fusion-skills AGENTS.md

aeon CLAUDE.md

ESAA-Core AGENTS.md