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 maystudios/claude-skills --skill midi-synthgit clone --depth 1 https://github.com/maystudios/claude-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/maystudios/claude-skills/midi-synth)<a href="https://agentmods.dev/skills/maystudios/claude-skills/midi-synth"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/midi-synth/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/maystudios/claude-skills/midi-synth"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/midi-synth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00187 | $0.01272 |
| Opus 5.5 | $0.00075 | $0.00509 |
| Sonnet 5.5 | $0.00037 | $0.00254 |
| Haiku 4.5 | $0.00019 | $0.00127 |
Grade A, and why
midi-synth 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MIDI Synth
Synthesize MIDI/MusicXML to audio and generate Strudel live-coding patterns. Uses analysis data for ghost-note cleaning, correct tempo, and key-aware filtering.
Scripts
scripts/to_strudel.py-- MIDI/MusicXML to Strudel patterns with duration-aware notationscripts/render.py-- MIDI/MusicXML to WAV/MP3 with cleaning and modifications
Both scripts auto-detect *_analysis.json files from audio-to-midi for tempo, key, and dynamics.
Workflow
- Identify input: MIDI (.mid) or MusicXML (.musicxml)
- Auto-detect or specify the analysis JSON from audio-to-midi
- Choose workflow:
- Creative:
to_strudel.pygenerates Strudel code for strudel.cc - Rendering:
render.pyproduces WAV/MP3 - Both: run both on the same input
- Creative:
- Ghost notes are automatically cleaned using velocity, duration, and key filters
Strudel Code Generation
# Basic (auto-detects analysis JSON next to input)
py -3.12 scripts/to_strudel.py "song.mid"
# From MusicXML
py -3.12 scripts/to_strudel.py "song.musicxml"
# Explicit analysis file
py -3.12 scripts/to_strudel.py "song.mid" --analysis "song_analysis.json"
# Stricter ghost-note filtering
py -3.12 scripts/to_strudel.py "song.mid" --min-velocity 60 --min-duration 0.1
# Open in browser
py -3.12 scripts/to_strudel.py "song.mid" --open
| Flag | Default | Effect |
|---|---|---|
--analysis |
auto-detect | Path to analysis JSON for tempo/key |
--bars |
4 | Pattern length in bars |
--resolution |
16 | Grid: 4/8/16/32 |
--min-velocity |
40 | Remove notes below this velocity (0-127) |
--min-duration |
0.05 | Remove notes shorter than this (seconds) |
--no-key-filter |
off | Disable key-based ghost note filtering |
--tempo |
from analysis | Override tempo BPM |
--open |
off | Open in strudel.cc in browser |
Note durations are encoded with @N notation (e.g., c3@4 = held for 4 steps).
Audio Rendering
# Basic (auto-detects analysis, cleans ghost notes)
py -3.12 scripts/render.py "song.mid" --mp3
# From MusicXML
py -3.12 scripts/render.py "song.musicxml" --mp3
# With SoundFont
py -3.12 scripts/render.py "song.mid" --soundfont "GeneralUser_GS.sf2" --mp3
# Aggressive cleaning
py -3.12 scripts/render.py "song.mid" --min-velocity 60 --min-duration 0.1
# Skip cleaning entirely
py -3.12 scripts/render.py "song.mid" --no-clean
# Modifications
py -3.12 scripts/render.py "song.mid" --tempo 2.0 --transpose 3 --instrument 0
What ships with it
3 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.
- 2mo ago First seen · 120 lines · 187 tokens per session scan A 5e9cfc2488de
midi-synth is a skill published in the GitHub repository maystudios/claude-skills (26 stars, last pushed 2mo ago), licensed MIT. It adds 187 tokens to every session and 1,272 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
timescaledb-hyperfunctions
Use this skill when writing analytical SQL over time-series data with the TimescaleDB Toolkit (timescaledbtoolkit extension) hyperfunctions: approximate percentiles, statistical summaries, time-weighted averages, counter/gauge rates, uptime/heartbeat tracking, state durations, OHLC candlesticks, approximate distinct…
postgres
Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations. Trigger when user asks to: Explore an existing PostgreSQL database to understand its objects and relationships Design or modify PostgreSQL tables…
cloudflare-development
Cloudflare Workers, Pages, KV, D1, R2, and Durable Objects development best practices for edge computing applications.
grpc-development
Best practices for building high-performance services with gRPC and Protocol Buffers. Use when designing RPC services, defining protobuf schemas, implementing streaming APIs, setting up gRPC interceptors, or building cross-language service communication.
kafka-development
Best practices for Apache Kafka event streaming and distributed messaging. Use when building event-driven architectures, implementing producer/consumer patterns, designing topic partitioning strategies, setting up Kafka Streams, configuring schema registries, or integrating change data capture pipelines.
kysely
Guidelines for developing with Kysely, a type-safe TypeScript SQL query builder with autocompletion support.