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 PerIPan/music-workflow-skills --skill song-to-abletongit clone --depth 1 https://github.com/PerIPan/music-workflow-skillsWrote 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/peripan/music-workflow-skills/song-to-ableton)<a href="https://agentmods.dev/skills/peripan/music-workflow-skills/song-to-ableton"><img src="https://agentmods.dev/badge/skills/peripan/music-workflow-skills/song-to-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/peripan/music-workflow-skills/song-to-ableton"><img src="https://agentmods.dev/badge/skills/peripan/music-workflow-skills/song-to-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 | $0.00053 | $0.01047 |
| Opus 5.5 | $0.00021 | $0.00419 |
| Sonnet 5.5 | $0.00011 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
song-to-ableton 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Song → Ableton (end-to-end orchestrator)
existing audio ──▶ A. ANALYSIS ──▶ C. HANDOFF ──▶ B. ABLETON (MCP)
stems · bars/BPM/key · chords bars + chords + build/reinterpret:
· bass MIDI · lyrics · drum read drum logic tempo · clips · MIDI
· devices · scenes · mix
ASK FIRST: "Do you want song analysis, Ableton building, or both?" Then route only to what's needed.
GOLDEN RULE: reason in BARS, never seconds. Every length and position is a bar count (1, 2, 4, 8, 16, 32…). Convert any "first 16 seconds" to bars and stay in bars.
Routing
| Need | Skill |
|---|---|
| Analyze the recording (tempo/bars, stems, chords, lyrics, drum read, chart) | song-analysis |
| Drive Live — tracks, clips, notes, devices, mixing; connection issues | ableton-mcp |
| Arrangement craft — sections, bass/drum patterns, FX chains, dynamics | ableton-arrangement |
| The user plays bass (or another mono instrument) and wants it as MIDI | bass-transcribe |
The handoff (analysis output → Ableton input)
| Analysis output | Use in Ableton |
|---|---|
pulse_bpm, pulse_unit, beats_per_bar, num_bars |
set_tempo(pulse_bpm × 4 / pulse_unit) — Live's tempo counts quarter notes. One bar = beats_per_bar × 4 / pulse_unit Live beats (4/4 → 4, 7/8 → 3.5, 11/8 → 5.5); size clips in whole bars |
chord_proposal per (bar, cell) |
chord clips on a synth/keys track, or a chart for a live band |
bar_bpm, tempo_drift_pct |
above ~±3% drift, place notes through the beat grid, not one BPM (ableton-mcp → "Timing") |
| bass MIDI (root line) | reference clip — or leave the bass slot empty for a live bassist |
| drum-pattern read | match the original's kick/snare logic (or generate_drum_pattern); never impose a rock backbeat on a non-rock song |
| key/mode | scale + voicings (mind major-triads-under-minor-melody — Trap 2 in song-analysis) |
| section map | scenes (jam) or arrangement sections; mirror parallel sections |
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 · +2 lines · -25 tokens per session e059907bcba6
- 2mo ago First seen · 69 lines · 78 tokens per session scan A e4394578b211
song-to-ableton is a skill published in the GitHub repository PerIPan/music-workflow-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,047 once invoked, about $0.0002 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 2026-08-31.
song-to-ableton compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| song-to-abletonPerIPan/music-workflow-skills | Skill | 3 | 1mo ago | MIT | A | 53 | Claude Code, Codex |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |
| accessibility-patternsvibeeval/vibecosystem | Skill | 539 | 2d ago | MIT | A | 24 | Claude Code, Codex |
| design-reviewjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 108 | Claude Code |
| react-patternsjezweb/claude-skills | Skill | 1.1k | 28d ago | MIT | A | 110 | Claude Code |