Borrowing it
Nothing to install: this file belongs to peerjakobsen/audiogen-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/peerjakobsen/audiogen-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/peerjakobsen/audiogen-mcpWrote 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/peerjakobsen/audiogen-mcp/claude-md)<a href="https://agentmods.dev/instructions/peerjakobsen/audiogen-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/peerjakobsen/audiogen-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/peerjakobsen/audiogen-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/peerjakobsen/audiogen-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00447 | $0.00447 |
| Opus 5 | $0.00224 | $0.00224 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
audiogen-mcp CLAUDE.md 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 8d 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.
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
AudioGen MCP Server
Project Overview
This is an MCP (Model Context Protocol) server that wraps Meta's AudioGen model for generating sound effects from text descriptions. It's designed to be used with Claude Code to generate game sound effects on-demand.
Quick Start
# Install and run
uvx audiogen-mcp
# Or for development:
pip install -e .
audiogen-mcp
Project Structure
audiogen-mcp/
├── src/audiogen_mcp/
│ ├── __init__.py
│ └── server.py # Main MCP server implementation
├── pyproject.toml # Package configuration
├── README.md # Full documentation
└── CLAUDE.md # This file
Available MCP Tools
- generate_sound_effect - Start a background generation job (returns job_id)
- check_generation_status - Poll for job completion (use after generate_sound_effect)
- list_generation_jobs - List all jobs and their status
- list_generated_sounds - List previously generated files
- get_model_status - Check model and device status
Key Technical Details
- Uses
facebook/audiogen-mediummodel - Apple Silicon: Uses MPS (Metal) for GPU acceleration
- Generation speed: ~60s per 5s of audio on M-series chips
- Output: WAV files at model's native sample rate (16kHz)
- Default output directory:
~/audiogen_outputs/
Example Usage in Claude Code
Once configured as an MCP server, you can ask Claude Code to:
- "Generate an explosion sound effect for the game"
- "Create a batch of UI sounds: click, hover, and error"
- "Make a retro 8-bit power-up sound, 2 seconds long"
Dependencies
- Python 3.9-3.11
- PyTorch with MPS support
- audiocraft (Meta's AudioGen)
- mcp (Model Context Protocol SDK)
- ffmpeg (system):
brew install ffmpeg
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.
- 8d ago First seen · 61 lines · 447 tokens per session scan A 9f3052de89a6
audiogen-mcp CLAUDE.md is an instructions file published in the GitHub repository peerjakobsen/audiogen-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 447 tokens to every session, about $0.0022 per session on Opus 5. 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.