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 Celian-mrc/serum-mcp --skill serum-sound-designgit clone --depth 1 https://github.com/Celian-mrc/serum-mcpWrote 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/celian-mrc/serum-mcp/serum-sound-design)<a href="https://agentmods.dev/skills/celian-mrc/serum-mcp/serum-sound-design"><img src="https://agentmods.dev/badge/skills/celian-mrc/serum-mcp/serum-sound-design/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/celian-mrc/serum-mcp/serum-sound-design"><img src="https://agentmods.dev/badge/skills/celian-mrc/serum-mcp/serum-sound-design.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 | $0.00118 | $0.01745 |
| Opus 5.5 | $0.00047 | $0.00698 |
| Sonnet 5.5 | $0.00024 | $0.00349 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
serum-sound-design 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 6d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serum sound design with serum-mcp
serum-mcp writes real .SerumPreset files straight into the user's Serum
presets folder. It has no model of its own: you turn the request into a
PresetSpec, the server validates and writes it. It never renders audio, so
you can't hear the result. Good presets come from following the rules below
and from studying real reference presets, not from guessing.
0. Check the server is available
Look for the tools generate_preset, edit_preset, describe_preset,
list_parameters, find_reference_presets, list_sample_files,
analyze_sample_file.
If they are missing, stop and tell the user that this skill needs the serum-mcp server. Point them to the install section of https://github.com/Celian-mrc/serum-mcp. They need:
- Python 3.11+ and
uv; uv syncin the cloned repo;- an MCP entry with
SERUM_PRESETS_PATHset to theirSerum 2 Presets/Presets/Userfolder.
Don't invent preset files by hand. The format is binary and undocumented.
1. Understand the request
Pin down three things:
- role: pad, lead, pluck, keys, bass, 808, arp, bell, texture, FX;
- character: dark/bright, static/evolving, clean/dirty, wide/mono;
- context: genre, artist, tempo feel.
If the user names a genre, artist or style, research it on the web before designing. Find the signature sounds, the typical processing, and what that genre avoids. A drill bank and a future-bass bank should not share an FX template.
For a bank (several presets), only include the roles the user asked for. Don't add basses or FX "to complete the set" unless they asked.
2. Study real references before writing a spec
- Call
find_reference_presets("<role> <character>"). Then calldescribe_preseton the 2–3 closest hits (factory or user presets). - Use them to set a complexity floor: how many oscillators, LFOs and mod routes, which macros, how long the FX chain is. Generated presets tend to be thinner than hand-made ones. Match or exceed the references.
- Call
list_parameters()whenever you're unsure of a range or enum value. Invalid enum names (a distortion mode that doesn't exist, a reverb width above its max) are rejected.
What ships with it
2 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.
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.
- 6d ago First seen · 138 lines · 118 tokens per session scan A 5f87f7483db0
serum-sound-design is a skill published in the GitHub repository Celian-mrc/serum-mcp (16 stars, last pushed 7d ago), licensed MIT. It adds 118 tokens to every session and 1,745 once invoked, about $0.0005 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 2026-10-14.
Other skills, from other repositories
suno-music
Use Suno through Ace Data Cloud in goose for Suno music, lyrics and covers. Use the installed service MCP tools; query the original task ID after generation. This plugin is maintained by Ace Data Cloud, not the service brand's official plugin.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
video-to-sfx
Generate sound effects matched to a video using Sonilo — footsteps, impacts, ambience, foley — optionally scripted to specific timed segments, returning either the audio or a new video with the SFX muxed in. Use when the user has footage that needs sound design. For SFX from a text description alone, use the…
audio-ducking
Duck a music bed under a voice track using Sonilo — automatically lowers the music wherever the voice speaks and lifts it back in the gaps. Use when mixing a separately-generated or existing music track under narration, dialogue, or a video's own voice track, without manual volume automation.
quantum-grover
A Qiskit implementation of Grover's algorithm, a quantum search method that increases the chance of finding a marked item. It can explain the method, build an explicit quantum circuit, or run it with chosen inputs.
dcc-blender-assembly-pitfalls
Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…