ableton-mcp-server: Instructions file for Codex

AGENTS.md

ableton-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from ntworm/ableton-mcp-server. It costs 2,090 tokens per session, scanned A, original, MIT.

Project instructions for ableton-mcp-server, a service that lets AI agents inspect and safely change Ableton Live Sets, which are Ableton's music-production project files.

In plain words
What is it for?
Guiding development of Ableton Live integration, including tool behavior, TCP and WebSocket communication, capability documentation, and known bugs.
Why use it?
They explain the supported tools, communication paths, platform requirements, documentation, and risks before an agent changes the code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is ntworm/ableton-mcp-server's own configuration. It tells Codex and OpenCode how to work on ableton-mcp-server 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 ableton-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ntworm/ableton-mcp-server. 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/ntworm/ableton-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ntworm/ableton-mcp-server

Made for: Codex, OpenCode.

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 ableton-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ntworm/ableton-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/ntworm/ableton-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ntworm/ableton-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ntworm/ableton-mcp-server/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.

agentmods 80×15 button for ableton-mcp-server AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ntworm/ableton-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ntworm/ableton-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,090 This file is loaded in full into every session.
When invoked 2,090 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 $0.02090 $0.02090
Opus 5.5 $0.00836 $0.00836
Sonnet 5.5 $0.00418 $0.00418
Haiku 4.5 $0.00209 $0.00209

Measured yesterday against content hash f11965eaf346, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ableton-mcp-server 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 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.

AGENTS.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — ableton-mcp-server

Purpose

ableton-mcp-server v0.8.1 exposes 97 MCP tools for inspecting and safely mutating an Ableton Live Set. Fourteen are local/headless and 83 may require Ableton Live; the current routes are loopback TCP, loopback WebSocket, composed local calls, and local-only tools. A Python FastMCP process coordinates a Live MIDI Remote Script over TCP and an Ableton Extension over WebSocket. The repository is MIT-licensed and targets Windows-hosted Ableton Live; WSL clients must launch the Windows-native executable.

Read order

  1. This file for repository-wide rules.
  2. Only the relevant .agent-context/{architecture,conventions,dependencies,hot-files,risks}.md file.
  3. Current source, tests, Git evidence, and canonical docs for task-specific claims.

Canonical project docs are README.md, docs/ARCHITECTURE.md, docs/TOOL_REFERENCE.md, docs/api_capability_matrix.md, and docs/KNOWN_BUGS.md. Files under prompts/ are proposals/handoffs and can be partially superseded; verify them against current code before acting.

Recent change context (read this if working on transport, capability matrix, or resolved envelope)

The v0.5.2 release landed four coordinated changes driven by the comparison with the public 8309/ableton-agent-hub project. Any agent picking up follow-up work should read the planning and handoff documents first to avoid re-litigating settled decisions:

  • docs/ABLETON_AGENT_HUB_REFACTORING.md — the original direction-setting plan (compare/contrast, scope decisions, items explicitly NOT to copy from the upstream project).
  • docs/superpowers/specs/2026-08-01-r1-resolved-field.md — the canonical shape of the resolved sub-object returned by mutation tools; deviating from this spec requires a new spec and a coordinated test update.
  • docs/superpowers/specs/2026-08-01-r4-capability-matrix.md — the design behind the new get_bridge_status.tools / capability_counts / capability_source fields; the spec contains a known non-blocking drift note about live_required_tools (57, not 59) that should be reconciled.
  • tasks/v0-5-1-refactor-r1r3/HANDOFF.md — the per-wave status and audit findings for v0.5.2. The current line subsequently implements the bounded R2/R6/E1 follow-ups described below.

Read the full file on GitHub · 111 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. yesterday Changed f11965eaf346
  2. 6d ago Changed · +181 tokens per session 72bde370c83d
  3. 1mo ago Changed a44352999df5
  4. 2mo ago First seen · 111 lines · 1,909 tokens per session scan A 9164c39d435f

Subscribe to this mod's changes

ableton-mcp-server AGENTS.md is an instructions file published in the GitHub repository ntworm/ableton-mcp-server (4 stars, last pushed 2d ago), licensed MIT. It adds 2,090 tokens to every session, about $0.0084 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.

Related

Other instructions, from other repositories

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 · 9,719 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 · 7,461 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,516 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 3,093 tokens

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.

deepseek-ai/deepseek-harness · 4,313 tokens