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 skills add freekmurze/ableton-ai --skill abletongit clone --depth 1 https://github.com/freekmurze/ableton-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/skills/freekmurze/ableton-ai/ableton)<a href="https://agentmods.dev/skills/freekmurze/ableton-ai/ableton"><img src="https://agentmods.dev/badge/skills/freekmurze/ableton-ai/ableton/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/freekmurze/ableton-ai/ableton"><img src="https://agentmods.dev/badge/skills/freekmurze/ableton-ai/ableton.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 | $0.00109 | $0.03254 |
| Opus 5 | $0.00055 | $0.01627 |
| Sonnet 5 | $0.00022 | $0.00651 |
| Haiku 4.5 | $0.00011 | $0.00325 |
Grade B, and why
ableton scanned grade B with 1 finding 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 9d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
So never tell the user something sounds good, warm, punchy, or lush. You don't How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Controlling Ableton Live
You are driving a real Live set that a musician cares about. Everything you do lands immediately in their project. Act accordingly.
The rule that governs everything: you cannot hear
You have no audio input. You can set a filter to 0.37 and confirm the value took, but you have no idea what came out of the speakers.
So never tell the user something sounds good, warm, punchy, or lush. You don't know. Describe what you built and what you verified, then let them judge.
Where you're genuinely useful is the tedious, mechanical work: 200 automation breakpoints, coprime loop lengths, phase offsets across six parameters, session scaffolding. Where you're useless is taste. Don't pretend otherwise.
Safety and hard limits
Ask before destructive work. Deleting tracks, clearing a set, or overwriting clips the user built by hand deserves a confirmation.
Live won't delete the last remaining track. Create the new one first, then delete the old.
There's no command for a new Live set. That's File, New Live Set, by hand.
Start here: resolve indices first
Before you act, resolve the indices you'll be working with. Call
get_session_info for the track list, then get_track_info for a track's
devices and clips. Every example below assumes you already know the right
track_index and device_index. Never guess them.
Verify everything. Status codes lie.
A success response does not mean the change happened. Always read the value
back.
This is not paranoia. Several commands return success while doing nothing, or while doing something different from what was asked. Read back after every change that matters:
# set it
cmd("set_device_parameter", {"track_index": 0, "device_index": 1,
"parameter_index": 5, "value": 0.42})
# then PROVE it
ps = cmd("get_device_parameters", {"track_index": 0, "device_index": 1})
If a read-back disagrees with what you asked for, say so plainly rather than reporting success.
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.
- 9d ago First seen · 280 lines · 109 tokens per session scan B 6c44ebbc52bd
ableton is a skill published in the GitHub repository freekmurze/ableton-ai (11 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 3,254 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.