cc-agents-kit: Instructions file for Claude Code

CLAUDE.md

cc-agents-kit CLAUDE.md is an instructions file for Claude Code from AndrewDongminYoo/cc-agents-kit. It costs 1,352 tokens per session, scanned D, original, Apache-2.0.

Project instructions for a Claude Code plugin marketplace. A plugin marketplace is a catalogue of add-ons, and this one contains shell hooks and JSON files rather than a normal application.

In plain words
What is it for?
Maintaining marketplace and plugin manifests, editing shell hooks, running their checks, and following the repository's layout and testing rules.
Why use it?
It clarifies the repository's unusual structure and the checks that matter, so changes do not break plugin discovery or hook behavior.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is AndrewDongminYoo/cc-agents-kit's own configuration. It tells Claude Code how to work on cc-agents-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cc-agents-kit configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to AndrewDongminYoo/cc-agents-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AndrewDongminYoo/cc-agents-kit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AndrewDongminYoo/cc-agents-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cc-agents-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andrewdongminyoo/cc-agents-kit/claude-md.svg)](https://agentmods.dev/instructions/andrewdongminyoo/cc-agents-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/andrewdongminyoo/cc-agents-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/andrewdongminyoo/cc-agents-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,352 This file is loaded in full into every session.
When invoked 1,352 The same file — it is already loaded in full.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01352 $0.01352
Opus 5 $0.00676 $0.00676
Sonnet 5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured 7d ago against content hash 1db9402251aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade D, and why

cc-agents-kit CLAUDE.md scanned grade D with 2 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

The same hooks are typically installed in the developing session's own `~/.claude/settings.json`, so they inspect the tool calls used to edit them.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Writing documentation or fixtures that *mention* a blocked shape — a download-and-execute pipeline, `rm -rf` on the home directory, a secrets filename — gets blocked when the text passes through `Bash`.
CLAUDE.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 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 repo is

A Claude Code plugin marketplace — not an application. Nothing here is imported or built; the artifacts are shell hooks plus the JSON manifests that make an installer find them. Every change is therefore judged on two things: does the manifest still resolve, and does the hook still hold its contract.

Commands

shellcheck plugins/*/hooks/*.sh
cd plugins/guard-hooks/hooks && for t in *.test.py; do python3 "$t" || exit 1; done
python3 plugins/guard-hooks/hooks/<name>.test.py     # a single suite
/bin/bash -n plugins/guard-hooks/hooks/<name>.sh     # macOS system bash 3.2, not your shell's bash

There is no build, no package manager, and no test framework. Suites are plain python3 scripts requiring bash and jq; shellcheck is optional (shellcheck-on-edit.test.py skips its findings checks and asserts the silent no-op instead). .github/workflows/ci.yml runs exactly the commands above plus manifest validation.

Layout contract

.claude-plugin/marketplace.json   # marketplace.json ONLY — no plugin.json here
plugins/<plugin>/
  .claude-plugin/plugin.json      # each plugin carries its own manifest
  hooks/hooks.json                # auto-discovered; commands reference ${CLAUDE_PLUGIN_ROOT}
  hooks/*.sh
  hooks/*.test.py                 # beside its hook, never in a tests/ directory
  hooks/_optout.py                # shared suite helper; leading _ keeps it out of the *.test.py glob

This mirrors Anthropic's own multi-plugin marketplace (claude-code-plugins), which is the layout to check against — not rn-agents-kit, whose single plugin uses "source": "./" and says nothing about nesting.

Two placements are load-bearing:

  • A source in marketplace.json that names a missing directory breaks installation for every user of the marketplace. Add the entry and the directory in the same commit.
  • Each suite resolves its hook with Path(__file__).resolve().with_name(...), and imports _optout as a plain sibling module. Moving either into its own directory silently breaks that, so they stay next to the scripts.

Read the full file on GitHub · 74 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. 7d ago First seen · 74 lines · 1,352 tokens per session scan D 1db9402251aa

Subscribe to this mod's changes

cc-agents-kit CLAUDE.md is an instructions file published in the GitHub repository AndrewDongminYoo/cc-agents-kit (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,352 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens