sonic-mcp: Instructions file for Claude Code

CLAUDE.md

sonic-mcp CLAUDE.md is an instructions file for Claude Code from AJBogo9/sonic-mcp. It costs 756 tokens per session, scanned A, original, MIT.

A project instruction file for an MCP server that connects Claude Code to Sonic Pi, a tool for creating music with code.

In plain words
What is it for?
Use it when working with Sonic Pi through the server, including starting, checking, and stopping Sonic Pi or sending musical commands.
Why use it?
It explains how to start Sonic Pi, discover its connection ports, and manage the connection without manual setup.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is AJBogo9/sonic-mcp's own configuration. It tells Claude Code how to work on sonic-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sonic-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AJBogo9/sonic-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.

Copy the file
curl -O https://raw.githubusercontent.com/AJBogo9/sonic-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AJBogo9/sonic-mcp

Made for: Claude Code.

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 sonic-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ajbogo9/sonic-mcp/claude-md.svg)](https://agentmods.dev/instructions/ajbogo9/sonic-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ajbogo9/sonic-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ajbogo9/sonic-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 756 This file is loaded in full into every session.
When invoked 756 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00756 $0.00756
Opus 5 $0.00378 $0.00378
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00076 $0.00076

Measured 7d ago against content hash af3256053c43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sonic-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 7d 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.

CLAUDE.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sonic-mcp -- Claude Code Instructions

This is the MCP server that connects Claude Code to Sonic Pi via OSC.

Starting Sonic Pi

Before using any tools, Sonic Pi must be running. Prefer headless mode:

sonicpi-headless   # start (waits until booted, then exits)
sonicpi-stop       # stop
sonicpi-status     # check status and current Spider port

If the scripts are not in PATH, they are in scripts/ in this repo. Install once with:

cp scripts/sonicpi-headless scripts/sonicpi-stop scripts/sonicpi-status ~/.local/bin/
chmod +x ~/.local/bin/sonicpi-{headless,stop,status}

The Qt GUI also works: pw-jack sonic-pi (required on Ubuntu 24.04 with PipeWire). Do NOT use the desktop shortcut -- it fails to open the audio device.

How the MCP server connects

The server auto-discovers the Spider server port from ~/.sonic-pi/log/server-output.log on first tool use. No manual configuration needed.

  • Headless mode: fixed UDP port 4557
  • Qt GUI mode: dynamic UDP port around 51235 (allocated at startup)
  • OSC cues (send_cue): always fixed UDP port 4560

The Spider client is lazily initialized, so tools work correctly whether Sonic Pi was started before or after the MCP server.

Workflow

  1. Start Sonic Pi: sonicpi-headless
  2. Use run_code to send code. Always follow with get_log to check for errors.
  3. Fix any errors before proceeding.
  4. Use stop_all to clear all playing loops before sending a full replacement.
  5. Save work with save_song (auto-increments version) or save_pattern.

stop_all vs sonicpi-stop

  • stop_all (MCP tool): stops all playing sounds. Sonic Pi keeps running. Use this between code iterations.
  • sonicpi-stop (terminal): shuts down the entire Sonic Pi process. Use this to end a session.

Port architecture

Sonic Pi 3.x runs several processes communicating over OSC:

Port Protocol Process Purpose
discovered from log UDP Ruby Spider server run code, stop, mixer controls
4560 UDP Erlang router OSC cue events (sync in Sonic Pi code)
4556 UDP scsynth (SuperCollider) audio synthesis
4561 UDP Erlang scheduler internal routing

Read the full file on GitHub · 75 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. 7d ago First seen · 75 lines · 756 tokens per session scan A af3256053c43

Subscribe to this mod's changes

sonic-mcp CLAUDE.md is an instructions file published in the GitHub repository AJBogo9/sonic-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 756 tokens to every session, about $0.0038 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens