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 glincker/ableton-skills --skill arrangement-coachgit clone --depth 1 https://github.com/glincker/ableton-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/glincker/ableton-skills/arrangement-coach)<a href="https://agentmods.dev/skills/glincker/ableton-skills/arrangement-coach"><img src="https://agentmods.dev/badge/skills/glincker/ableton-skills/arrangement-coach/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/glincker/ableton-skills/arrangement-coach"><img src="https://agentmods.dev/badge/skills/glincker/ableton-skills/arrangement-coach.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 | $0.00079 | $0.00955 |
| Opus 5 | $0.00039 | $0.00477 |
| Sonnet 5 | $0.00016 | $0.00191 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
arrangement-coach 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 11d 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.
Arrangement Coach
Promote a Session-view loop into a structured Arrangement, or extend a short idea into a full-length track. The user owns the musical content; you handle structural decisions.
Workflow
1. Read what they have
get_session_info— confirm session vs arrangement stateget_track_infofor each track — collect all clips currently in Session view- Identify the loop length (most likely 4 or 8 bars) and the BPM
2. Choose a structural template
Ask the user once: "Which structure?"
| Template | Length | Sections |
|---|---|---|
| Pop | ~3 min | Intro 8 → V1 16 → Pre 8 → Chorus 16 → V2 16 → Pre 8 → Chorus 16 → Bridge 8 → Chorus 16 → Outro 8 |
| EDM | ~4 min | Intro 16 → Build 16 → Drop 32 → Break 32 → Build 16 → Drop 32 → Outro 16 |
| Lo-fi | 2-3 min | Intro 4 → Loop A x4 → Variation x2 → Loop A x2 → Tail 4 |
| Cinematic | varies | Stmt → Dev → Climax → Resolution. Use rubato; bar count flexible. |
| Hip-hop | 2-3 min | Intro 4 → V1 16 → Hook 8 → V2 16 → Hook 8 → Bridge/V3 16 → Hook 8 → Outro 4 |
3. Promote loops to arrangement
For each section in the template:
- Identify which Session clips fit (most loops can serve multiple sections by muting/unmuting tracks)
- Use
create_arrangement_clip(or equivalent) to drop clips at the right bars on the right tracks - Mute tracks that shouldn't play in that section (intro = drums + bass only; chorus = everything; bridge = strip back)
4. Add transitions
- Risers before drops (if EDM/pop) — white noise sweep, snare roll, reverse cymbal
- Drum fills at section boundaries — tom roll into the chorus
- Filter automation — high-pass sweep into a build, low-pass into a break
- Reverb tail throw — send the last hit of a section through the delay/reverb return
5. Master fader automation (subtle)
- -1 to -3 dB dip in breakdowns
- Slight push (+0.5 dB) into final chorus
- Don't ride more than 3 dB; let the mix do the work
6. Confirm
Before applying, summarize: "I'll build a 2:48 EDM structure: intro 16, build 16, drop 32, break 32, build 16, drop 32, outro 16. Drum fills at every section boundary, filter sweep into builds, master fader -2 dB in break. Apply?"
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.
- 11d ago First seen · 71 lines · 79 tokens per session scan A a3c829e20a9d
arrangement-coach is a skill published in the GitHub repository glincker/ableton-skills (25 stars, last pushed 18d ago), licensed MIT. It adds 79 tokens to every session and 955 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 2026-08-30.
Other skills, from other repositories
ableton-live
Connect and operate the Loophole Bridge (Ableton Live MCP server). Use when the user wants to check Live/bridge prerequisites, wire an MCP client to Loophole, or run a Live editing recipe (humanize, build arrangement, batch rename, chord from prompt). Triggers: "is my Ableton bridge working", "set up loophole"…
livepilot-creative-director
Use when the user makes an open-ended creative production request — "make it feel like X", "sound like X", "develop this", "mutate", "more interesting", "less generic", "take it somewhere", structure decisions without exact specs, or any reference/style ask. Also use when routerequest returns…
livepilot-core
Core discipline for LivePilot — agentic production system for Ableton Live 12. 474 tools across 57 domains. This skill should be used whenever working with Ableton Live through MCP tools. Provides golden rules, tool speed tiers, error handling protocol, and pointers to domain and engine skills.
livepilot-corpus-builder
Build a private knowledge corpus from your own Live projects, rack library, Max devices, and plugin presets. Use when the user says "build my corpus", "scan my projects", "index my racks", "make atlas of my library", "private atlas from my files", or wants Claude to know their personal sound (not just Ableton's…
livepilot-sound-design-engine
This skill should be used when the user asks to "design a sound", "analyze a patch", "fix a static sound", "add modulation", "check my timbre", "improve a synth patch", or wants critic-driven sound design feedback and iterative patch refinement.
livepilot-devices
This skill should be used when the user asks to "load a device", "add an effect", "find a plugin", "device chain", "rack", "preset", "sound design setup", "load instrument", "find a synth", or wants to browse, load, and configure devices in Ableton Live.