Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/opendining/ableton-mcp-server/ableton-guidenpx skills add opendining/ableton-mcp-server --skill ableton-guidegit clone --depth 1 https://github.com/opendining/ableton-mcp-serverWrote 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/skills/opendining/ableton-mcp-server/ableton-guide)<a href="https://agentmods.dev/skills/opendining/ableton-mcp-server/ableton-guide"><img src="https://agentmods.dev/badge/skills/opendining/ableton-mcp-server/ableton-guide.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.00933 |
| Opus 5 | $0.00036 | $0.00466 |
| Sonnet 5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
ableton-guide 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ableton Live MCP — Agent Guide
You control Ableton Live by sending Python code via the execute tool. Each call is a fresh scope with these variables:
song, app, tracks, returns, master, browser, Live, MidiNoteSpecification, find_item, find_items, find_track, load_to, log, json, time
Use api() and search_api(query) to explore the Live API reference.
Built-in Helpers
These are in scope every call — no imports or definitions needed.
MidiNoteSpecification(pitch, start_time, duration, velocity) — create MIDI note specs:
clip.add_new_notes(tuple([
MidiNoteSpecification(pitch=60, start_time=0.0, duration=0.5, velocity=100),
]))
find_item(parent, query) — search a browser tree for the best-matching loadable item (case-insensitive, breadth-first, prefers exact matches). Returns BrowserItem or None:
find_item(browser.instruments, "Grand Piano")
find_item(browser.drums, "808") # finds "808 Core Kit" not a random 808 sample
find_item(browser.audio_effects, "Reverb")
find_items(parent, query, limit=20) — like find_item but returns a ranked list. Use when you want to see candidates:
find_items(browser.drums, "808") # → [808 Core Kit.adg, 808 variants…, individual 808 hits…]
find_track(name) — look up a track by name (case-insensitive). Returns Track or None:
bass = find_track("Bass")
bass.mixer_device.volume.value = 0.8
load_to(track, parent, query) — find a browser item, select the track, and load it. Returns the BrowserItem. Raises ValueError if nothing matched:
load_to(song.tracks[0], browser.instruments, "Grand Piano")
load_to(find_track("Drums"), browser.drums, "808")
Gotchas
- Fresh scope each call. Variables/functions from a previous
executedon't carry over. - Track indices shift after create/delete. Use
find_track(name)orsong.tracks(not thetracksshortcut, which is a stale snapshot). - Can't delete the last track. Loop from the end:
for i in range(len(song.tracks) - 1, 0, -1): song.delete_track(i) - Multi-line code can partially execute. If line 5 fails, lines 1–4 already ran. Use
song.undo()to roll back. time.sleep(0.3)between consecutive browser loads (load_toorbrowser.load_item). Without it, loads silently fail.- No export API. Tell the user to export manually (Ctrl+Shift+R / Cmd+Shift+R).
- Return data with
result. Expressions return their value directly. For statements, assign toresult:result = [(i, t.name) for i, t in enumerate(song.tracks)]
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.
- 4d ago First seen · 90 lines · 71 tokens per session scan A 609a74ee81f1
ableton-guide is a skill published in the GitHub repository opendining/ableton-mcp-server (1 stars, last pushed 6mo ago), licensed MIT. It adds 71 tokens to every session and 933 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…