claude-code-plugin CLAUDE.md

claude-code-plugin CLAUDE.md is an instructions file for coding agents from anilcancakir/claude-code-plugin. It costs 3,290 tokens per session, scanned B, original, MIT.

Instructions for a multi-plugin Claude Code marketplace whose main plugin provides planning, execution, setup, and extension-building commands.

In plain words
What is it for?
Planning and carrying out coding tasks, running autonomous work across turns, configuring Claude Code, and creating skills, agents, commands, rules, and instruction files.
Why use it?
They explain how the marketplace and its main workflow fit together, including automatic execution and reminders for the user's own coding rules.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/anilcancakir/claude-code-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugin

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 claude-code-plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anilcancakir/claude-code-plugin/claude-md.svg)](https://agentmods.dev/instructions/anilcancakir/claude-code-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/anilcancakir/claude-code-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/anilcancakir/claude-code-plugin/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,290 This file is loaded in full into every session.
When invoked 3,290 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.03290 $0.03290
Opus 5 $0.01645 $0.01645
Sonnet 5 $0.00658 $0.00658
Haiku 4.5 $0.00329 $0.00329

Measured 3d ago against content hash 41de888b9605, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-code-plugin CLAUDE.md scanned grade B with 1 finding 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 3d 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.

This is a **multi-plugin marketplace** for Claude Code. The main plugin `ac` ships a main-agent planning trio (`/ac:plan`, `/ac:execute`, `/ac:wisdom`) with an autonomous execution mode (`/ac:execute --auto`, sticky stat
CLAUDE.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 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.

Mission

This is a multi-plugin marketplace for Claude Code. The main plugin ac ships a main-agent planning trio (/ac:plan, /ac:execute, /ac:wisdom) with an autonomous execution mode (/ac:execute --auto, sticky state file, ScheduleWakeup cross-turn loop), plus setup, init, and commit commands and creator skills for building Claude Code extensions (skills, agents, commands, rules, CLAUDE.md files). The planning trio runs entirely in the main agent (no subagent swarms, no tier routing); /ac:setup-global-claude-md blocks EnterPlanMode, ExitPlanMode, and Agent(Plan) in ~/.claude/settings.json so the ac trio owns planning end-to-end. Two hooks back the workflow: SessionStart reminds Claude to invoke the user's personal my-coding and my-language twin skills (and re-injects autonomous-run state on resume), PreCompact preserves run state in the summarization prompt. The marketplace structure allows additional plugins to be added independently.

Architecture

├── .claude-plugin/
│   └── marketplace.json          # Plugin catalog — all plugins registered here
├── plugins/
│   ├── ac/                       # Main plugin: planning trio + autonomous execution + creator skills + 2 hooks
│   │   ├── .claude-plugin/
│   │   │   └── plugin.json       # Minimal: name, description, author
│   │   ├── .mcp.json             # MCP server configs (kodizm bundled)
│   │   ├── commands/             # 9 user-invocable /ac:* commands (plan, execute, wisdom, commit, init-*, setup-*)
│   │   ├── hooks/                # session-start.mjs (twin-skill + autonomous resume), pre-compact.mjs (state preservation)
│   │   ├── skills/
│   │   │   ├── prompt-writer/    # Shared CC prompt writing foundation + references/
│   │   │   ├── skill-creator/    # Skill creation + references/
│   │   │   ├── agent-creator/    # Agent creation + references/
│   │   │   ├── command-creator/  # Command creation + references/
│   │   │   ├── rule-creator/     # Rule creation
│   │   │   └── claude-md-writer/ # CLAUDE.md authoring + references/
│   │   ├── references/           # Templates for setup/init commands, CLAUDE.md generation, and execution-state schema
│   │   ├── README.md
│   │   └── LICENSE
│   ├── github-cli/               # GitHub CLI skill plugin
│   ├── github-actions/           # GitHub Actions workflow generator plugin
│   ├── git-master/               # Git expert skill plugin
│   ├── frontend-design/          # Frontend design skill plugin
│   ├── dart-lsp/                 # Dart/Flutter language server plugin
│   ├── json-lsp/                 # JSON language server plugin
│   ├── yaml-lsp/                 # YAML language server plugin
│   └── markdown-lsp/             # Markdown language server plugin
├── CLAUDE.md                     # This file
├── README.md                     # Marketplace README
├── package.json
└── LICENSE

Read the full file on GitHub · 137 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. 3d ago First seen · 137 lines · 3,290 tokens per session scan B 41de888b9605

Subscribe to this mod's changes

claude-code-plugin CLAUDE.md is an instructions file published in the GitHub repository anilcancakir/claude-code-plugin (2 stars, last pushed 4mo ago), licensed MIT. It adds 3,290 tokens to every session, about $0.0164 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.