Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/instructions/husniadil/cc-hooks/claude-md)<a href="https://agentmods.dev/instructions/husniadil/cc-hooks/claude-md"><img src="https://agentmods.dev/badge/instructions/husniadil/cc-hooks/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.08589 | $0.08589 |
| Opus 5 | $0.04294 | $0.04294 |
| Sonnet 5 | $0.01718 | $0.01718 |
| Haiku 4.5 | $0.00859 | $0.00859 |
Grade B, and why
cc-hooks CLAUDE.md scanned grade B with 2 findings 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Check server logs: `tail -f ~/.claude/.cc-hooks/logs/{claude_pid}.log` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:12222/health How it starts
The opening of the file, as written. The whole thing — 1,121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Development guide for cc-hooks - a Claude Code hooks processing system with TTS announcements and contextual AI.
Documentation Structure
- README.md - Plugin installation (recommended for most users)
- STANDALONE_README.md - Standalone installation (for developers/contributors)
- MIGRATION.md - Migration guide from standalone to plugin mode
- CLAUDE.md - This file: Development and technical guide
Best Practices
PEP 723 for Standalone Scripts
All test scripts, utilities, and one-off tools MUST use PEP 723 for dependency management:
#!/usr/bin/env -S uv run --script
# /// script
# dependencies = ["aiosqlite", "python-dotenv"]
# ///
Why:
- Self-contained with explicit dependencies
- No global environment pollution
- Works across different machines
- Easy to run:
uv run script.py
Database Migrations
CRITICAL RULES:
- One SQL statement per migration - Never combine multiple statements
- Append-only - Never modify existing migrations that are deployed
- Sequential versions - Always increment from the latest version
Code Style
- Clean, readable code with minimal single-line comments
- Self-contained, reusable components
- Direct communication (no sugar-coating in error messages)
- Practical over perfect
Quick Start
Plugin Mode (Recommended):
# Set up alias first (add to .bashrc/.zshrc)
alias cld='~/.claude/plugins/marketplaces/cc-hooks-plugin/claude.sh'
# Start Claude Code with cc-hooks
cld
# Common configurations
cld --audio=gtts --language=id
cld --audio=elevenlabs --ai=full
cld --silent=announcements
Standalone Mode:
# From cc-hooks directory
./claude.sh
# Common configurations
./claude.sh --audio=gtts --language=id
./claude.sh --audio=elevenlabs --ai=full
./claude.sh --silent=announcements
Project Overview
Purpose: Middleware that processes Claude Code hook events with audio feedback and contextual AI messages.
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.
- 6d ago First seen · 1,121 lines · 8,589 tokens per session scan B 720a7f74dd06
cc-hooks CLAUDE.md is an instructions file published in the GitHub repository husniadil/cc-hooks (19 stars, last pushed 7mo ago), licensed MIT. It adds 8,589 tokens to every session, about $0.0429 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
speech-mcp AGENTS.md
AGENTS.md instructions for sandraschi/speech-mcp, covering agents.md — speech-mcp, project identity, architecture quick reference, ports and code rules.
speech-mcp GEMINI.md
Gemini CLI instructions for sandraschi/speech-mcp, covering speech-mcp: system context, 🛠 tech stack, 📡 registry & ports, 🏗 directory structure and 🧠 development standards.
speech-mcp copilot-instructions.md
Copilot instructions for sandraschi/speech-mcp, covering github copilot instructions — speech-mcp and session context (speech mcp).
speech-mcp CLAUDE.md
Claude Code instructions for sandraschi/speech-mcp, covering speech-mcp — claude code guide, entry points, standards and key files.
rikkahub AGENTS.md
AGENTS.md instructions for rikkahub/rikkahub, covering repository guidelines, project overview, build, test, and development commands, module structure and concepts.
agentops CLAUDE.md
Claude Code instructions for boshu2/agentops, a project described as: The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.