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 adamjmurray/producer-pal --skill ableton-audio-generatorgit clone --depth 1 https://github.com/adamjmurray/producer-palWrote 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/adamjmurray/producer-pal/ableton-audio-generator)<a href="https://agentmods.dev/skills/adamjmurray/producer-pal/ableton-audio-generator"><img src="https://agentmods.dev/badge/skills/adamjmurray/producer-pal/ableton-audio-generator/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/adamjmurray/producer-pal/ableton-audio-generator"><img src="https://agentmods.dev/badge/skills/adamjmurray/producer-pal/ableton-audio-generator.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 | $0.00144 | $0.01843 |
| Opus 5.5 | $0.00058 | $0.00737 |
| Sonnet 5.5 | $0.00029 | $0.00369 |
| Haiku 4.5 | $0.00014 | $0.00184 |
Grade A, and why
ableton-audio-generator 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ableton Audio Generator
Write DSP in plain Node.js, render .wav files, and get them into Ableton Live.
You write the algorithm. The library writes the file. Every request is a
different sound, so there is no default generator to run — read the request,
design the synthesis for it, and use lib/ for the parts that are the same
every time.
Division of labor
| Yours | The library's |
|---|---|
| Oscillators, envelopes, filters, noise, modulation, the structure | WAV encoding (encodeWav / writeWav) |
| Deciding what "gritty" or "glassy" means in DSP terms | Peak normalize across channels |
| Frame counts, lengths, layering, how many voices | declick so one-shots don't pop |
| Everything that makes this sound different from the last one | Flag parsing and range checks (lib/cli.mjs) |
The library covers exactly the failures that are silent — a malformed header, a clicking tail, a table whose geometry doesn't line up. Those don't announce themselves; they just sound broken. Anything you can hear and judge is yours.
Pick a target, then read its doc
Each target has its own format contract and its own way of landing in Live. Read the one you need — do not work from this page alone.
| The user wants | Read | Lands in Live by |
|---|---|---|
| A drone, texture, riser, bed, any standalone audio | targets/audio-clip.md |
Automated — clip on an audio track |
| One sound to play chromatically from a sampler | targets/simpler-sample.md |
Automated — replace_sample |
| A full kit across pads | targets/drum-kit.md |
Automated — one Drum Rack call |
| A wavetable to sweep through | targets/wavetable.md |
Manual drag onto an oscillator |
| A convolution reverb space | targets/reverb-ir.md |
Manual drag onto Hybrid Reverb |
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- cookbook.md 11 KB
- examples/example-drone.mjs 3.7 KB runs code
- examples/example-ir.mjs 3.5 KB runs code
- examples/example-kit.mjs 5.6 KB runs code
- examples/example-wavetable.mjs 4.3 KB runs code
- lib/audio-io.mjs 10 KB runs code
- lib/cli.mjs 3.2 KB runs code
- targets/audio-clip.md 3.9 KB
- targets/drum-kit.md 3.7 KB
- targets/reverb-ir.md 3.8 KB
- targets/simpler-sample.md 2.9 KB
- targets/wavetable.md 4.6 KB
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.
- 1mo ago Changed a388924a6df8
- 2mo ago First seen · 151 lines · 144 tokens per session scan A d422afd1d194
ableton-audio-generator is a skill published in the GitHub repository adamjmurray/producer-pal (361 stars, last pushed 3d ago), licensed MIT. It adds 144 tokens to every session and 1,843 once invoked, about $0.0006 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 2026-08-30.
ableton-audio-generator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ableton-audio-generatoradamjmurray/producer-pal | Skill | 361 | 3d ago | MIT | A | 144 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |