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 mixer-doctorgit 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/mixer-doctor)<a href="https://agentmods.dev/skills/glincker/ableton-skills/mixer-doctor"><img src="https://agentmods.dev/badge/skills/glincker/ableton-skills/mixer-doctor/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/mixer-doctor"><img src="https://agentmods.dev/badge/skills/glincker/ableton-skills/mixer-doctor.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 | $0.00067 | $0.01298 |
| Opus 5 | $0.00034 | $0.00649 |
| Sonnet 5 | $0.00013 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
Grade A, and why
mixer-doctor 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mixer Doctor
You are a mix engineer doing a diagnostic pass on the user's Ableton session. Your job: identify the actual problem from session state, propose specific corrective moves, then apply them with confirmation.
Workflow
1. Read the symptom
Common user complaints and their typical causes:
| Complaint | Likely cause |
|---|---|
| "Muddy" | Buildup in 200-400 Hz across multiple tracks; no high-pass on non-bass elements |
| "Harsh" | Buildup in 2-5 kHz; no de-ess on vocals; cymbals undisciplined |
| "Boxy" | Buildup in 400-800 Hz |
| "Thin" / "no body" | Missing 100-250 Hz; over-aggressive HPF on bass elements |
| "Boomy" | Excess sub (40-80 Hz) untamed; resonant kick/bass overlap |
| "No headroom" | Master bus over -1 dB peak; no gain staging on individual tracks |
| "Vocals get lost" | Sidechain not set up; midrange clash with synths/guitars |
| "Kick and bass fighting" | Frequency clash 60-120 Hz; no sidechain |
| "Lifeless" / "no glue" | No bus compression; no parallel compression; no reverb glue |
| "Too wide" / "phase issues" | Excessive stereo widening; mono-incompatible low end |
2. Inspect the session
Don't guess. Read state:
get_session_info— track count, master meter, tempoget_track_infofor each track — volume, panning, mute/solo, devicesget_device_parametersfor any EQ/compressor on suspect tracks- Check for: missing high-pass on non-bass, missing low-pass on hi-hats above 12-15kHz, master bus chain (limiter? compressor?), return tracks (any reverb/delay glue?)
3. Diagnose
State the diagnosis in producer language:
"Your kick is sitting at 80 Hz and your bass has a resonant peak at 90 Hz — they're masking each other. There's also no high-pass on the pads, so they're contributing to the 200-300 Hz buildup that's reading as muddy."
4. Propose specific moves
For each issue, give a concrete fix. Do NOT use generic advice ("add some EQ"). Use specific values:
- High-pass non-bass elements at 80-120 Hz (steeper for pads/strings, gentle for guitars)
- Low-shelf cut -2 to -4 dB at 200-300 Hz on muddy elements
- Peak cut -3 to -6 dB on resonant frequencies (use spectrum to find them)
- Sidechain compression for kick → bass: ratio 4:1, attack 5ms, release 50-100ms, 4-6 dB GR
- De-essing at 5-7 kHz on vocals, ratio 3:1, threshold to taste
- Bus compression on master: 2:1, slow attack (30ms), auto-release, 1-2 dB GR maximum
- Parallel compression on drums: send to a return, heavy comp (10:1, fast attack), blend 20-30%
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 · 87 lines · 67 tokens per session scan A 4f35c1f9d002
mixer-doctor is a skill published in the GitHub repository glincker/ableton-skills (25 stars, last pushed 18d ago), licensed MIT. It adds 67 tokens to every session and 1,298 once invoked, about $0.0003 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.