Borrowing it
Nothing to install: this file belongs to peterkolbe/ableton-for-ai. 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/peterkolbe/ableton-for-ai/main/AGENTS.mdgit clone --depth 1 https://github.com/peterkolbe/ableton-for-aiWrote 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/peterkolbe/ableton-for-ai/agents-md)<a href="https://agentmods.dev/instructions/peterkolbe/ableton-for-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/peterkolbe/ableton-for-ai/agents-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/peterkolbe/ableton-for-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/peterkolbe/ableton-for-ai/agents-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 | $0.02455 | $0.02455 |
| Opus 5.5 | $0.00982 | $0.00982 |
| Sonnet 5.5 | $0.00491 | $0.00491 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
ableton-for-ai AGENTS.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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents Guide for Ableton-for-AI
This document provides essential technical context for AI agents working on this project.
Project Purpose
The goal is to provide a bridge between Ableton Live and AI-driven tools (like Mix-Engineers or LLMs) to enable automated mixing, analysis, and data extraction of music projects.
Core Components
1. osc_daemon.py (The Bridge)
- Role: A persistent background service that converts JSON-RPC over TCP into OSC over UDP.
- API Documentation: Whenever an agent needs to access Ableton via the
osc_daemon, they MUST first consult the AbletonOSC README to ensure they are using the correct OSC addresses and parameter specifications. - Ports:
- Listens for JSON-RPC on
127.0.0.1:65432. - Sends OSC to Ableton on
11000. - Receives OSC from Ableton on
11001.
- Listens for JSON-RPC on
- Key Features:
- Request/Response Matching: Uses a
request_idand tracks pending futures to handle the asynchronous nature of OSC. - Wildcard Support: Can handle OSC wildcard queries (e.g.,
/live/track/get/*) and correctly dispatch multiple responses. - Tolerant Matching: Handles slight data type mismatches (int vs float) that AbletonOSC sometimes returns.
- OSC Bundling: Supports grouped OSC messages in a single UDP packet for atomic execution and high performance.
- Request/Response Matching: Uses a
2. ableton_client.py (The Interface)
- Role: High-level Python API for interacting with the
osc_daemon. - Key Operations:
get_tracks: Uses the highly efficient/live/song/get/track_dataprotocol for mass metadata retrieval.extract_ableton_project_data: Quick extraction of project metadata, tracks, and device parameters.get_available_stems/get_available_spectrograms: List available analysis results from previous runs.analyze_stems: Independent audio analysis pipeline (spectrograms + energy) without project data.
analyze_stems_and_extract_ableton_project_data: The full pipeline that gathers project data AND triggers deep audio analysis. Required to enable audio-related resources.set_device_parameter/set_track_volume: Remote control methods to modify the Live session.
- Rate Limiting: Uses an
asyncio.Semaphore(limit: 50) to prevent overwhelming the Ableton Remote Script while allowing high parallelism for parameter retrieval.
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.
- 2mo ago First seen · 133 lines · 2,455 tokens per session scan A db7fc37ea730
ableton-for-ai AGENTS.md is an instructions file published in the GitHub repository peterkolbe/ableton-for-ai (1 stars, last pushed 5mo ago), licensed MIT. It adds 2,455 tokens to every session, about $0.0098 per session on Opus 5.5. 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.
ableton-for-ai AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ableton-for-ai AGENTS.mdpeterkolbe/ableton-for-ai | Instructions file | 1 | 5mo ago | MIT | A | 2,455 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |