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.
npx agentmods add skills/chanmeng666/echook/audio-hooksnpx skills add ChanMeng666/echook --skill audio-hooksgit clone --depth 1 https://github.com/ChanMeng666/echookWrote 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/skills/chanmeng666/echook/audio-hooks)<a href="https://agentmods.dev/skills/chanmeng666/echook/audio-hooks"><img src="https://agentmods.dev/badge/skills/chanmeng666/echook/audio-hooks.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 | $0.00321 | $0.10067 |
| Opus 5 | $0.00161 | $0.05033 |
| Sonnet 5 | $0.00064 | $0.02013 |
| Haiku 4.5 | $0.00032 | $0.01007 |
Grade C, and why
audio-hooks scanned grade C 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| `AUDIO_PLAYER_NOT_FOUND` | No mpg123/ffplay/aplay on Linux, or PowerShell missing on Windows | `sudo apt install mpg123` (Linux) | Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Unlike Claude Code, **Codex does not support a command-backed status line**. Codex renders only *fixed lists of built-in item IDs* configured under `[tui].status_line` and `[tui].terminal_title` in `~/.codex/config.toml` How it starts
The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audio-hooks skill
This plugin is the AI control surface for the echook project. The user does NOT operate this project by hand. You operate it on their behalf via the audio-hooks binary that this plugin adds to your Bash tool's PATH.
Golden rule: when in doubt about the project's current capabilities, run audio-hooks manifest first. The manifest is the canonical machine description of every subcommand, every config key, every hook, every audio file, and every error code. It is always up to date with the running version. Treat this SKILL.md as an orientation; treat audio-hooks manifest as the source of truth.
What the user can ask for and what you should run
Install / set up the project
The plugin install (which you are using right now) is the recommended path for Claude Code users. If a user is not yet on the plugin, tell them to run /plugin marketplace add ChanMeng666/echook and /plugin install audio-hooks@chanmeng-audio-hooks inside Claude Code. Cursor IDE 3.2.16+ users get audio-hooks for free via Cursor's built-in third-party hooks bridge — no separate Cursor install needed. For users who run Cursor without Claude Code, use audio-hooks install --cursor (see "Install for Cursor-only users" below). Codex users should use the Codex plugin path when available, or audio-hooks install --codex as the native hooks.json fallback — Codex does NOT auto-bridge Claude Code plugins (see "Install for Codex users" below). Once installed, verify with:
audio-hooks status
audio-hooks test all
Snooze / mute / quiet hours
| User says | Run |
|---|---|
| "snooze audio for 30 minutes" | audio-hooks snooze 30m |
| "shut up for an hour" | audio-hooks snooze 1h |
| "mute audio for the rest of the day" | audio-hooks snooze 8h |
| "unmute" / "resume" / "cancel snooze" | audio-hooks snooze off |
| "is audio snoozed?" | audio-hooks snooze status |
Duration syntax: 30m, 1h, 90s, 2d, or a bare integer (interpreted as minutes).
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.
- 4d ago First seen · 560 lines · 321 tokens per session scan C e4b25e0aeb25
audio-hooks is a skill published in the GitHub repository ChanMeng666/echook (86 stars, last pushed 4d ago), licensed MIT. It adds 321 tokens to every session and 10,067 once invoked, about $0.0016 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pronounce-word
User asks how to pronounce an English word or project/product name ("how to pronounce X", "pronounce X", "X 怎么读", "X 怎么发音", "读一下 X"). Generate audio via the say-it CLI so the user actually HEARS the word — three times by default — instead of only writing IPA/syllable hints. The CLI consults a community-maintained…
code-snippet-images
Generate beautiful code snippet images (PNG) for social media, tweets, LinkedIn, and documentation. Creates light-themed, macOS-style window chrome screenshots from code using HTML templates and Chrome headless. Use when asked to create code images, tweet images, snippet screenshots, code cards, or visual code…
audit
Audit local Claude Code transcript usage and summarize likely token hotspots. Use when the user asks where Claude Code tokens are going or wants evidence before optimizing.
ableton
Control Ableton Live through the AbletonMCP tools. Use when the user wants to build tracks, patches, clips, drums, automation, or generative music in Ableton, or asks to change any device, mixer, or transport setting in their Live set. Triggers on "Ableton", "Live set", "make a patch", "build a track", "add a synth"…
optimize
Diagnose and reduce Claude Code token usage for a project or session using context hygiene, model and effort routing, MCP minimization, output trimming/sanitizing, subagent discipline, and measurement. Use when the user asks to lower Claude Code token usage, cost, context bloat, or usage-limit burn.
setup
Interactive or guided project setup for Claude Code token optimizer settings. Use when the user asks to install, configure, setup, enable hooks, or choose token-saving options interactively.