Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Celian-mrc/serum-mcpnpx agentmods add skills/celian-mrc/serum-mcp/test-in-serumWrote 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/test-in-serum)<a href="https://agentmods.dev/skills/celian-mrc/serum-mcp/test-in-serum"><img src="https://agentmods.dev/badge/skills/celian-mrc/serum-mcp/test-in-serum/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/test-in-serum"><img src="https://agentmods.dev/badge/skills/celian-mrc/serum-mcp/test-in-serum.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 | $0.00108 | $0.00872 |
| Opus 5.5 | $0.00043 | $0.00349 |
| Sonnet 5.5 | $0.00022 | $0.00174 |
| Haiku 4.5 | $0.00011 | $0.00087 |
Grade A, and why
test-in-serum 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 2mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test a serum-mcp preset before asking the user to load it
This project's own hard-won lesson (see docs/PARAMETER_SCHEMA.md and
CONTRIBUTING.md): unit tests and round-trip checks are not sufficient
to prove a generated preset works. The first fully-tested preset this
project shipped still crashed FL Studio ~2 seconds after being selected,
from a CBOR wire-type mismatch no amount of self-consistent round-tripping
could catch. That specific failure class is now automatable; whether the
preset actually sounds right, or loads without some other real-Serum-only
issue, is not -- that part still needs the user.
Steps
-
Run the automated scan on every preset file involved:
uv run python scripts/check_preset.py "<path-to-preset>" ["<path-to-preset-2>" ...]If mid-session code changes to
src/serum_mcp/haven't been picked up by a normaluv runyet (e.g. the entry-point.exeis locked by a connected MCP server process, a known Windows gotcha this session hit repeatedly), useuv run --no-sync python scripts/check_preset.py ...instead. -
If it reports FAIL (a CBOR wire-type issue): stop -- do not tell the user to load the file. This means a real bug slipped past
preset/validator.py's normalization. Go fixpreset/mapping.py(or wherever the offending value was written), rerun the scan, and only proceed once it's clean. This is a hard gate, not a warning to note and move past. -
If it reports OK: summarize the preset's key sections (oscillators, filters, envelope shape, FX chain, mod routes -- whatever's relevant to what was just generated/edited) for the user in a few lines, pointing out anything worth specifically checking in Serum's UI (e.g. "a new FX type that's never been tested live before", "a custom-synthesized wavetable", "an edited param that should have changed vs. what should have stayed the same").
-
Ask the user to load it and report back -- don't declare the feature/fix done based on the scan alone. If this was verifying a fix for something the user already reported, be specific about what changed and what you want them to check (the original symptom, not just "does it work").
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.
- 2mo ago First seen · 61 lines · 108 tokens per session scan A 051bb4d6f78c
test-in-serum is a skill published in the GitHub repository Celian-mrc/serum-mcp (20 stars, last pushed 16d ago), licensed MIT. It adds 108 tokens to every session and 872 once invoked, about $0.0004 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.
Other skills, from other repositories
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
opik-test
Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the compare skill. Works over the SDK; uses the MCP write tool when connected. Returns the suite, the item, and the assertion.…
evm-audit-flow
Use when you have a Foundry or Hardhat repository of Solidity or Vyper contracts and want the end-to-end EVM review workflow on native CLIs — a slither static pass, semgrep taint rules, mythril symbolic execution, echidna and medusa invariant fuzzing, halmos formal checks, then a forge build-and-test regression.
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.