What is claude-code CLAUDE.md?

A guide to Claude Code plugins, which extend Claude Code with reusable hooks, shared utilities, and integrations such as GitHub workflows or project-context checks.

Use it to build or install Claude Code plugins, create session hooks, configure hooks.json, use plugin project paths, and troubleshoot hooks that do not run.

It shows the expected plugin structure and hook conventions, reducing setup mistakes such as incorrect imports, paths, or configuration variables.

claude-code CLAUDE.md — Instructions file by constellos

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/constellos/claude-code/claude-md

Clone the repo

git clone --depth 1 https://github.com/constellos/claude-code

Per session 403 This file is loaded in full into every session.

When invoked 403 The same file — it is already loaded in full.

Security scan C 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.

Model	Per session	Once invoked
Fable 5	$0.00403	$0.00403
Opus 5	$0.00201	$0.00201
Sonnet 5	$0.00081	$0.00081
Haiku 4.5	$0.00040	$0.00040

Measured 2d ago against content hash 8935b21708fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

claude-code 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 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.

Recursive force deletehighDestructive command

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

- **Cache stale**: `rm -rf ~/.claude/plugins/cache/constellos && claude plugin install --scope project`

CLAUDE.md · 64 lines

What it actually says

Claude Code Plugins

Plugin marketplace with shared TypeScript utilities for typed hooks.

Plugins

Plugin	Purpose
github-orchestration	GitHub workflow orchestration, branch context, CI
project-context	CLAUDE.md discovery, validation
nextjs-supabase-ai-sdk-dev	Vercel/Supabase, UI dev system

Hook Pattern

import type { SessionStartInput, SessionStartHookOutput } from '../shared/types/types.js';
import { runHook } from '../shared/hooks/utils/io.js';

async function handler(input: SessionStartInput): Promise<SessionStartHookOutput> {
  return {
    hookSpecificOutput: {
      hookEventName: 'SessionStart',
      additionalContext: 'Hook executed',
    },
  };
}

export { handler };
runHook(handler);

Important: Imports use ../shared/ (plugin-local), NOT ../../../shared/ (repo root).

hooks.json

{
  "hooks": {
    "SessionStart": [{ "hooks": [{ "type": "command", "command": "npx tsx ${CLAUDE_PLUGIN_ROOT}/hooks/my-hook.ts" }] }]
  }
}

Variables: ${CLAUDE_PROJECT_DIR}, ${CLAUDE_PLUGIN_ROOT}

Installation

claude plugin install plugin-name@constellos

Troubleshooting

Hooks not firing: Check ~/.claude/plugins/cache/, reinstall plugin, restart session
Cache stale: rm -rf ~/.claude/plugins/cache/constellos && claude plugin install --scope project

Debug

DEBUG=hook-name claude

Logs: .claude/logs/hook-events.json

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 · 64 lines · 403 tokens per session scan C 8935b21708fb

Subscribe to this mod's changes

claude-code CLAUDE.md is an instructions file published in the GitHub repository constellos/claude-code (5 stars, last pushed 4mo ago), licensed MIT. It adds 403 tokens to every session, about $0.0020 per session on Opus 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.

Debugging

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 · 5,182 tokens

buildNext

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

claude-code CLAUDE.md