Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/mlmil/ableton-live-mcp-ultra-v2/ableton-hermes-operator)<a href="https://agentmods.dev/skills/mlmil/ableton-live-mcp-ultra-v2/ableton-hermes-operator"><img src="https://agentmods.dev/badge/skills/mlmil/ableton-live-mcp-ultra-v2/ableton-hermes-operator/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/skills/mlmil/ableton-live-mcp-ultra-v2/ableton-hermes-operator"><img src="https://agentmods.dev/badge/skills/mlmil/ableton-live-mcp-ultra-v2/ableton-hermes-operator.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 | $0.00071 | $0.01718 |
| Opus 5 | $0.00036 | $0.00859 |
| Sonnet 5 | $0.00014 | $0.00344 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
ableton-hermes-operator 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 12d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ableton Hermes Operator
Use this skill for the local Hermes-driven Ableton workflow. The primary server is the bschoepke-style Ableton Live MCP (server name ableton), patched with named lifecycle, convenience, and fade tools (server version 0.2.0+, Remote Script runtime lifecycle-fade-wrappers-1).
MCP Setup
Known installed paths:
- MCP repo (installed):
/Users/tomservo/Documents/Codex/ableton-live-mcp - Canonical patched source:
/Volumes/Kenobi/Ableton MCPs/bschoepke:ableton-mcp/ableton-live-mcp-main - Remote Script:
/Users/tomservo/Music/Ableton/User Library/Remote Scripts/Ableton_Live_MCP - Agent Audio Tap device:
/Users/tomservo/Music/Ableton/User Library/Presets/Audio Effects/Max Audio Effect/AgentAudioTap.amxd
If the new tools below are missing from the tool list, the installed copy is stale: sync it from the canonical patched source, reinstall the Remote Script (src/install_remote_script.py), and reload Live. live_ping reports the Remote Script runtime version; expect lifecycle-fade-wrappers-1 or later.
Ableton must have Control Surface Ableton_Live_MCP selected in Preferences > Link, Tempo & MIDI.
Validate the bridge first:
live_ping({})
Expected: ok: true. If a call stalls, check live_bridge_status before retrying mutations.
Main Live Set
Primary set:
/Users/tomservo/Desktop/Sin Chonies Gig Folder/SinChonies1 Project/SinChonies1.als
Open it when needed:
open "/Users/tomservo/Desktop/Sin Chonies Gig Folder/SinChonies1 Project/SinChonies1.als"
Confirm through MCP:
live_get({"ref": {"path": "live_set"}, "properties": ["name", "file_path"]})
Expected name: SinChonies1.
Audio Interface
Ableton should use the Behringer XR18: CoreAudio, input and output XR18 (18 In, 18 Out), Main Out 1/2, Cue Out 1/2. Verify through the Ableton UI if routing is suspect.
Named Tools (preferred)
Prefer these named tools over raw live_exec/live_call equivalents:
| Tool | Use |
|---|---|
live_fade |
Timed fader fades (see Fade Convention) |
live_fire_clip / live_stop_clip |
Launch/stop Session clips by track_index + clip_index or ref |
live_set_tempo |
Set BPM (20–999) |
live_create_midi_track / live_create_audio_track |
Create tracks; index: -1 appends; optional name |
live_rename_track |
Rename by ref, track_index, or master: true |
live_lifecycle_status |
Check whether Live API save/quit exists on this install |
live_save_set |
Save via song.save() if available; else returns the GUI workflow |
live_quit_ableton |
Save-then-quit; schedules quit so the response returns |
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.
- 12d ago First seen · 153 lines · 71 tokens per session scan A 0955c1808461
ableton-hermes-operator is a skill published in the GitHub repository mlmil/Ableton-Live-MCP-ULTRA-v2 (1 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 1,718 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…