agentmods.dev

claude-ableton: Instructions file for Claude Code

CLAUDE.md

claude-ableton CLAUDE.md is an instructions file for Claude Code from rohailaltaf/claude-ableton. It costs 1,604 tokens per session, scanned A, original, MIT.

A set of instructions for claude-ableton, a plugin that lets a coding agent control Ableton Live 12, music-production software, through a local server. It explains the code layout, release process, and known problems.

In plain words
What is it for?
It helps maintain the TypeScript server, its music-control tools, bundled files, installer, build output, and tests against Ableton Live.
Why use it?
It gives agents the project-specific details needed to change or release the plugin without rediscovering its setup and constraints.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is rohailaltaf/claude-ableton's own configuration. It tells Claude Code how to work on claude-ableton 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 claude-ableton configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 2repo 2mo ago A scan 1,604 tokens original MIT
View source ↗ rohailaltaf/claude-ableton
Reuse

Borrowing it

Nothing to install: this file belongs to rohailaltaf/claude-ableton. 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/rohailaltaf/claude-ableton/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rohailaltaf/claude-ableton

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 claude-ableton CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rohailaltaf/claude-ableton/claude-md.svg)](https://agentmods.dev/instructions/rohailaltaf/claude-ableton/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rohailaltaf/claude-ableton/claude-md"><img src="https://agentmods.dev/badge/instructions/rohailaltaf/claude-ableton/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,604 This file is loaded in full into every session.
When invoked 1,604 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 $0.01604 $0.01604
Opus 5 $0.00802 $0.00802
Sonnet 5 $0.00321 $0.00321
Haiku 4.5 $0.00160 $0.00160

Measured 8d ago against content hash 0a268bbf75a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-ableton 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.

CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — working notes for Claude in this repo

claude-ableton is a Claude plugin (a Node/TypeScript MCP server) that drives Ableton Live 12 via a bundled, pinned fork of AbletonOSC. It's distributed GitHub-natively: this one repo is both the marketplace and the plugin.

Layout

  • src/*.ts — the server. tools.ts (all 139 MCP tools), osc.ts (hand-rolled OSC over dgram), chords.ts (voice-leading), installer.ts (Option-B Remote Script installer), index.ts (entry), server.ts, context.ts, constants.ts, types.ts (shared Note/RhythmStep/AutomationStep shapes).
  • dist/index.js — committed esbuild bundle (zero runtime deps). This is what the plugin actually runs.
  • vendor/AbletonOSC/ — committed pinned Remote Script, generated by scripts/vendor-remote-script.mjs (clones the fork at PINNED_REF).
  • .claude-plugin/plugin.json — plugin manifest. Declares the MCP server inline (mcpServers.ableton → node ${CLAUDE_PLUGIN_ROOT}/dist/index.js) and holds the version.
  • .claude-plugin/marketplace.json — marketplace; the plugin's source is "./".
  • scripts/ — build.mjs (esbuild), vendor-remote-script.mjs, integration-test.mjs (live 139-tool test), list-tools.mjs, smoke-send.ts.
  • skills/ — bundled Agent Skills (auto-discovered, namespaced claude-ableton:<name>). One per subdirectory (SKILL.md with name/description frontmatter). Shipped: mastering-chain. When writing a new skill, probe live Ableton for REAL device parameter names first (don't guess them) and bump the plugin version so users receive it.

Release runbook — do this when asked to "do a release"

  1. Make changes under src/.
  2. npm run typecheck && npm run build — rebuilds the committed dist/index.js.
  3. If the AbletonOSC fork changed: set PINNED_REF in scripts/vendor-remote-script.mjs to the new fork commit, run npm run vendor, and stage vendor/AbletonOSC/.
  4. Bump version (semver) in BOTH .claude-plugin/plugin.json AND package.json — keep them identical. Claude reads plugin.json's version; users only receive auto-updates when this string changes. (If version were omitted, Claude would fall back to the git commit SHA instead.)
  5. Commit everything, including the rebuilt dist/index.js (and vendor/ if it changed).
  6. Tag and push: git tag -a vX.Y.Z -m "…" && git push origin main && git push origin vX.Y.Z. (The git tag is for humans; Claude's update logic uses plugin.json's version.)
  7. Users on auto-update get it next startup → prompted to run /reload-plugins. Auto-update is off by default for third-party marketplaces (each user enables it per-marketplace via /plugin → Marketplaces → Enable auto-update); manual update is /plugin marketplace update claude-ableton → /reload-plugins.

Read the full file on GitHub · 92 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. 8d ago First seen · 92 lines · 1,604 tokens per session scan A 0a268bbf75a5

Subscribe to this mod's changes

claude-ableton CLAUDE.md is an instructions file published in the GitHub repository rohailaltaf/claude-ableton (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,604 tokens to every session, about $0.0080 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.

Creative and mediaabletonclaudeclaude-code-pluginmcpmcp-server
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 · 5,153 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