clooks: Instructions file for Claude Code

CLAUDE.md

clooks CLAUDE.md is an instructions file for Claude Code from mauribadnights/clooks. It costs 929 tokens per session, scanned A, original, MIT.

A project instruction file for clooks, a persistent local HTTP service that receives Claude Code hook events and sends them to configured handlers. Hooks are automatic actions triggered by events such as tool use or session changes.

In plain words
What is it for?
Use it when working on clooks or its repository instructions. It documents building, testing, type-checking, benchmarking, and the main server, command-line, and plugin components.
Why use it?
It gives contributors a shared description of the project’s commands, architecture, and tests. This avoids having to rediscover how the daemon routes requests or how the project is checked.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is mauribadnights/clooks's own configuration. It tells Claude Code how to work on clooks 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 clooks configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mauribadnights/clooks. 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/mauribadnights/clooks/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mauribadnights/clooks

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 clooks CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mauribadnights/clooks/claude-md.svg)](https://agentmods.dev/instructions/mauribadnights/clooks/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mauribadnights/clooks/claude-md"><img src="https://agentmods.dev/badge/instructions/mauribadnights/clooks/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 929 This file is loaded in full into every session.
When invoked 929 The same file — it is already loaded in full.
Security scan A 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 5.1 $0.00929 $0.00929
Opus 5 $0.00464 $0.00464
Sonnet 5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured 6d ago against content hash 6082b575dc0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

clooks CLAUDE.md scanned grade A 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

Tests mirror `src/` — one test file per module in `tests/`. Tests use vitest. Most tests mock the filesystem and child_process to avoid touching `~/.clooks/` or `~/.claude/`. When writing tests, use dependency injection
CLAUDE.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 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 is clooks

Persistent HTTP daemon that replaces Claude Code's per-invocation process spawning for hooks. Claude Code POSTs hook events to 127.0.0.1:7890, which dispatches to handlers defined in ~/.clooks/manifest.yaml. Three handler types: script (subprocess), inline (in-process JS import), llm (Anthropic API call with prompt templates and batching).

Commands

npm run build          # tsc → dist/
npm test               # vitest run (all tests)
npm run test:watch     # vitest watch mode
npx vitest run tests/filter.test.ts   # single test file
npx tsc --noEmit       # type-check only
npm run bench          # performance benchmarks (npx tsx benchmarks/bench.ts)

Architecture

The daemon is a plain Node.js HTTP server (no frameworks). Request flow:

  1. cli.ts — Commander-based CLI, entry point (bin: clooks). Handles start/stop/status/migrate/doctor/plugins/service commands.
  2. server.ts — HTTP server creation, hook routing (POST /hooks/:eventName), auth, session agent caching, deny cache short-circuiting, manifest hot-reload via file watcher.
  3. handlers.ts — Execution engine. Resolves dependency order into waves (via deps.ts), runs each wave in parallel. Separates async (fire-and-forget) from sync handlers. Auto-disables handlers after 3 consecutive failures. Resolves the user's login shell PATH at startup so script handlers work under launchd/systemd.
  4. llm.ts — LLM handler execution with two backends: api (Anthropic SDK, supports batching and cost tracking) and claude-code (spawns claude -p, supports --agent). API handlers sharing a batchGroup are combined into a single API call. Cost tracking writes to ~/.clooks/costs.jsonl (API backend only).
  5. manifest.ts — Loads and validates manifest.yaml. loadCompositeManifest() merges user manifest with plugin-contributed handlers.
  6. plugin.ts — Plugin install/remove/list. Plugins are directories with clooks-plugin.yaml. Handler IDs are namespaced (pluginName/handlerId).
  7. migrate.ts — Converts existing settings.json command hooks into HTTP hooks pointing at the daemon. Creates backup.
  8. service.ts — Platform-native service management (launchd on macOS, systemd on Linux).

Read the full file on GitHub · 46 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. 6d ago First seen · 46 lines · 929 tokens per session scan A 6082b575dc0b

Subscribe to this mod's changes

clooks CLAUDE.md is an instructions file published in the GitHub repository mauribadnights/clooks (2 stars, last pushed 5mo ago), licensed MIT. It adds 929 tokens to every session, about $0.0046 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

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

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

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

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

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