What is claude-code-plugin-automations CLAUDE.md?

Repository instructions for developing Claude Code plug-ins, including agents, skills, commands, and hooks. They describe the project structure and require validation before changes are committed.

Use them when creating or modifying plug-in components. They point to validation scripts, component-building tools, and templates for each supported component type.

They reduce the chance of committing malformed plug-in components or changes that fail the repository's checks.

How C0ntr0lledCha0s/claude-code-plugin-automations configures Claude C

Reuse

Borrowing it

Nothing to install: this file belongs to C0ntr0lledCha0s/claude-code-plugin-automations. 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/C0ntr0lledCha0s/claude-code-plugin-automations/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/C0ntr0lledCha0s/claude-code-plugin-automations

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/c0ntr0lledcha0s/claude-code-plugin-automations/claude-md/github.svg)](https://agentmods.dev/instructions/c0ntr0lledcha0s/claude-code-plugin-automations/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/c0ntr0lledcha0s/claude-code-plugin-automations/claude-md"><img src="https://agentmods.dev/badge/instructions/c0ntr0lledcha0s/claude-code-plugin-automations/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/c0ntr0lledcha0s/claude-code-plugin-automations/claude-md"><img src="https://agentmods.dev/badge/instructions/c0ntr0lledcha0s/claude-code-plugin-automations/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,266 This file is loaded in full into every session.

When invoked 5,266 The same file — it is already loaded in full.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.05266	$0.05266
Opus 5.5	$0.02106	$0.02106
Sonnet 5.5	$0.01053	$0.01053
Haiku 4.5	$0.00527	$0.00527

Measured 2mo ago against content hash eb4370abce5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

claude-code-plugin-automations CLAUDE.md scanned grade C 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 2mo 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.

Recursive force deletehighDestructive command

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

- **Review bash commands**: Audit for dangerous operations like `rm -rf`

CLAUDE.md · 467 lines

How it starts

The opening of the file, as written. The whole thing — 467 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.

⚠️ CRITICAL: Always Validate Before Committing

MANDATORY: Before creating ANY commit with plugin components (agents, skills, commands, hooks), you MUST:

Run validation scripts on all modified components:

# Quick validation of everything
bash validate-all.sh

# Or validate individual components:
python3 claude-component-builder/skills/building-agents/scripts/validate-agent.py path/to/agent.md
python3 claude-component-builder/skills/building-skills/scripts/validate-skill.py path/to/skill/
python3 claude-component-builder/skills/building-commands/scripts/validate-command.py path/to/command.md
python3 claude-component-builder/skills/building-hooks/scripts/validate-hooks.py path/to/hooks.json

Fix ALL critical errors before committing. The pre-commit hook will block commits with validation errors.
Use claude-component-builder tools when creating/modifying components:
- Invoke the building-agents, building-skills, building-commands, or building-hooks skills
- Use templates from claude-component-builder/skills/*/templates/
- Reference examples from claude-component-builder/skills/*/references/

Why this matters: Validation catches security vulnerabilities, naming issues, and structural problems BEFORE they become part of git history.

Repository Overview

This is a meta-repository containing Claude Code plugins. It's essentially Claude building tools for Claude - a collection of meta-agents, skills, commands, and hooks that extend Claude Code's capabilities.

Key Concept: This repository contains plugins that help build other plugins. The Claude Component Builder plugin is a "meta-plugin" - a plugin that creates other plugins and their components.

Plugin Architecture

Available Plugins

Total: 7 plugins | 16 agents | 35 skills | 59 commands

Read the full file on GitHub · 467 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.

2mo ago First seen · 467 lines · 5,266 tokens per session scan C eb4370abce5e

Subscribe to this mod's changes

claude-code-plugin-automations CLAUDE.md is an instructions file published in the GitHub repository C0ntr0lledCha0s/claude-code-plugin-automations (3 stars, last pushed 9mo ago), licensed MIT. It adds 5,266 tokens to every session, about $0.0211 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

claude-code-plugin-automations CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-plugin-automations CLAUDE.mdC0ntr0lledCha0s/claude-code-plugin-automations	Instructions file	3	9mo ago	MIT	C	5,266	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode

claude-code-plugin-automations: Instructions file for Claude Code