daw-mcp: Instructions file for Claude Code

CLAUDE.md

daw-mcp CLAUDE.md is an instructions file for Claude Code from ptaczek/daw-mcp. It costs 3,688 tokens per session, scanned A, original, MIT.

Project instructions for daw-mcp, an MCP server that lets Claude control the clip-launching view of Bitwig Studio and Ableton Live, which are digital audio workstations. It does not cover the timeline-based arrangement view.

In plain words
What is it for?
Use it when building or changing the DAW server, its Bitwig and Ableton extensions, development setup, or workflows where AI creates clips and a person arranges them into songs.
Why use it?
It defines the supported music workflow and limits the project to addressable track-and-clip slots, avoiding unsupported timeline operations.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is ptaczek/daw-mcp's own configuration. It tells Claude Code how to work on daw-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 daw-mcp configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/pta/Games/ableton.

Reuse

Borrowing it

Nothing to install: this file belongs to ptaczek/daw-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/ptaczek/daw-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ptaczek/daw-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 daw-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ptaczek/daw-mcp/claude-md.svg)](https://agentmods.dev/instructions/ptaczek/daw-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ptaczek/daw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ptaczek/daw-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,688 This file is loaded in full into every session.
When invoked 3,688 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 $0.03688 $0.03688
Opus 5 $0.01844 $0.01844
Sonnet 5 $0.00738 $0.00738
Haiku 4.5 $0.00369 $0.00369

Measured 7d ago against content hash cf4ce5ac0cf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

daw-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 · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DAW MCP Project

MCP server for controlling DAWs (Bitwig Studio, Ableton Live) from Claude.

Scope: Session View / Clip Launcher Only

This project intentionally targets only the clip launcher (Bitwig) / session view (Ableton) paradigm. Arrangement view is out of scope.

Rationale:

  • Clip launcher provides discrete, addressable units (track × slot) - ideal for AI-driven workflows
  • Arrangement view has continuous timeline addressing - fragile, less intuitive for AI
  • Bitwig's Control Surface API doesn't expose arrangement clips at all
  • Ableton's API has arrangement access, but asymmetric support across DAWs is undesirable
  • The user arranges clips into songs - that's human creative territory

Implications:

  • No arrangement clip creation, reading, or note manipulation
  • No Reaper support (Reaper lacks a clip launcher paradigm entirely)
  • MIDI/OSC alternatives were considered but rejected - not worth the complexity

Workflow: AI generates clips in launcher slots → User arranges them into songs on timeline.

Project Structure

  • bitwig-extension/ - Java extension for Bitwig Studio (TCP server on port 8181)
  • ableton-extension/ - Python MIDI Remote Script for Ableton Live (port 8182)
  • mcp-server/ - TypeScript MCP server that bridges Claude to DAW extensions

Building (Development)

# Bitwig extension
cd bitwig-extension && gradle build && gradle copyExtension

# MCP server
cd mcp-server && npm install && npm run build

Release Build

Creates a distributable ZIP with all components:

./scripts/release.sh 1.0.0

Output: release/daw-mcp-1.0.0.zip (~325KB)

Contents:

  • BitwigMCP.bwextension - Java extension (cross-platform, single file)
  • AbletonMCP/ - Python Remote Scripts (cross-platform)
  • mcp-server.js - Bundled MCP server (~215KB, requires Node.js)
  • config.example.json - Example configuration
  • README.md - Installation instructions

How it works:

  1. Builds Bitwig extension via Gradle
  2. Bundles MCP server with esbuild into single JS file
  3. Copies Ableton Python scripts
  4. Creates ZIP archive

Read the full file on GitHub · 396 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 · 396 lines · 3,688 tokens per session scan A cf4ce5ac0cf1

Subscribe to this mod's changes

daw-mcp CLAUDE.md is an instructions file published in the GitHub repository ptaczek/daw-mcp (16 stars, last pushed 8mo ago), licensed MIT. It adds 3,688 tokens to every session, about $0.0184 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 2026-08-30.

Related

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.

vercel/next.js · 7,296 tokens

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

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

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

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