claude-code-curated-hooks CLAUDE.md

claude-code-curated-hooks CLAUDE.md is an instructions file for coding agents from normful/claude-code-curated-hooks. It costs 598 tokens per session, scanned B, original, MIT.

Project instructions for working with Claude Code hooks, which are scripts triggered by events such as tool use or notifications.

In plain words
What is it for?
They are for understanding, adding, testing, and installing hooks in the curated hook collection.
Why use it?
They explain the repository structure and the required format for its shell and Python hook scripts.

Instructions file

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/normful/claude-code-curated-hooks/claude-md
Clone the repo
git clone --depth 1 https://github.com/normful/claude-code-curated-hooks

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-curated-hooks CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/normful/claude-code-curated-hooks/claude-md.svg)](https://agentmods.dev/instructions/normful/claude-code-curated-hooks/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/normful/claude-code-curated-hooks/claude-md"><img src="https://agentmods.dev/badge/instructions/normful/claude-code-curated-hooks/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 598 This file is loaded in full into every session.
When invoked 598 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 $0.00598 $0.00598
Opus 5 $0.00299 $0.00299
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 5d ago against content hash 75d648534124, 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-curated-hooks 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 5d 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.

- `~/.claude/settings.json` (global personal settings)
CLAUDE.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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.

Project Overview

This is a curated collection of Claude Code hooks - automation scripts that trigger on Claude Code events. The project supports two types of hooks:

  1. One-liner hooks (bash scripts in one-liners/) - Simple shell commands
  2. Python hooks (Python scripts in py-hooks/) - More complex hooks using the cchooks library

Architecture

Core Components

  • install-hook.sh - Interactive installation script that installs hooks to Claude Code settings files
  • one-liners/ - Directory containing bash one-liner hook scripts
  • py-hooks/ - Directory containing Python hook scripts that use the cchooks library
  • tests/ - Comprehensive test suite using bashunit framework

Hook Script Format

One-liner hooks follow this format:

# event: PostToolUse
# matcher: Write|Edit|MultiEdit
command_to_execute

Python hooks use metadata comments and the cchooks library:

#!/usr/bin/env -S uv run --script
# ... other comments about dependencies, added by uv
# event: Notification
# matcher: *

# ... hook implementation in Python, using the cchooks libray

Installation Process

The install-hook.sh script:

  1. Lists available hooks from both directories
  2. Extracts metadata (event, matcher, command) from selected script
  3. Prompts user to choose installation location:
    • .claude/settings.local.json (personal project settings)
    • .claude/settings.json (team project settings)
    • ~/.claude/settings.json (global personal settings)
  4. Uses jq to manipulate JSON and install the hook

Development Commands

Running Bash Unit Tests

# Run all tests (auto-installs bashunit if needed)
./run-bash-tests.sh

Installing Hooks

./install-hook.sh

Dependencies

  • jq - Required for JSON manipulation during hook installation
  • bashunit - Testing framework (auto-installed by test script)
  • uv - For Python hook execution (Python hooks use #!/usr/bin/env -S uv run --script)
  • terminal-notifier - Required for macOS notification hooks

Read the full file on GitHub · 86 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. 5d ago First seen · 86 lines · 598 tokens per session scan B 75d648534124

Subscribe to this mod's changes

claude-code-curated-hooks CLAUDE.md is an instructions file published in the GitHub repository normful/claude-code-curated-hooks (1 stars, last pushed 1y ago), licensed MIT. It adds 598 tokens to every session, about $0.0030 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.