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 plugins/chanmeng666/echook/marketplace/plugin marketplace add ChanMeng666/echookgit clone --depth 1 https://github.com/ChanMeng666/echookGrade A, and why
chanmeng-audio-hooks scanned grade A with 0 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 yesterday.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "chanmeng-audio-hooks",
"owner": {
"name": "Chan Meng",
"url": "https://github.com/ChanMeng666"
},
"metadata": {
"description": "Audio notifications for Claude Code, Cursor IDE & Codex CLI, configured in natural language. 39 hook events + 44 matcher variants, each with its own sound. Desktop toasts without a terminal, TTS, webhook fan-out, status line + per-subagent rows, rate-limit alerts. Auto-bridges to Cursor 3.2.16+; native install for Cursor-only via 'audio-hooks install --cursor'; native install for Codex via 'audio-hooks install --codex'.",
"version": "6.5.0"
},
"plugins": [
{
"name": "audio-hooks",
"source": "./plugins/audio-hooks",
"version": "6.5.0",
"description": "Audio notifications + AI-controlled config for Claude Code, Cursor IDE, and Codex CLI events. Auto-bridges to Cursor 3.2.16+; native install for Cursor via 'audio-hooks install --cursor' and for Codex via 'audio-hooks install --codex'.",
"author": {
"name": "Chan Meng",
"url": "https://github.com/ChanMeng666"
},
"homepage": "https://github.com/ChanMeng666/echook",
"repository": "https://github.com/ChanMeng666/echook",
"license": "MIT",
"keywords": ["audio", "notifications", "hooks", "tts", "webhook", "ai-operated", "rate-limits", "status-line", "cursor", "cursor-ide", "codex", "codex-cli", "openai-codex"]
}
]
}
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.
- yesterday First seen · 28 lines scan A 6afcc24fbb75
chanmeng-audio-hooks is a plugin published in the GitHub repository ChanMeng666/echook (86 stars, last pushed 9d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
context-guard
Marketplace for ContextGuard: Claude Code context hygiene, token/cost visibility, and local guardrails.
context-guard
ContextGuard keeps AI coding-agent context lean, safe, and auditable with project-local setup, scans, large-read guards, output trimming/sanitizing, queryable log artifacts, budgeted context packs, tool/MCP schema pruning, statusline visibility, and usage audits.
music
Ableton Live control skills.
sounds
Audio notifications for Claude Code events.
claude-sound-notification
Plays different sounds when Claude Code finishes a task vs needs your input. Cross-platform.
claude-sound-notification
Plugin marketplace listing 1 plugin: claude-sound-notification.