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 mazumba/opencode-dockerized --skill midigit clone --depth 1 https://github.com/mazumba/opencode-dockerizedWrote 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/mazumba/opencode-dockerized/midi)<a href="https://agentmods.dev/skills/mazumba/opencode-dockerized/midi"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/midi/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/mazumba/opencode-dockerized/midi"><img src="https://agentmods.dev/badge/skills/mazumba/opencode-dockerized/midi.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 | $0.00045 | $0.00509 |
| Opus 5.5 | $0.00018 | $0.00204 |
| Sonnet 5.5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
midi 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 15d 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.
What it actually says
The container is headless: there is no sound card and no notation renderer (no MuseScore or LilyPond). Write results to files.
Choosing a library
| Task | Library | Notes |
|---|---|---|
| Raw messages, tempo maps, byte-exact edits | mido 1.3 |
Times are delta ticks. Convert with mido.tick2second. |
| Notes in seconds: generate, quantise, transpose | pretty_midi 0.2 |
Instrument(program=0..127) takes General MIDI programs. Drums use is_drum=True. |
| Theory: keys, chords, intervals, MusicXML | music21 10 |
converter.parse("x.mid").analyze("key"). Calling .show() raises an error here. Use .write("musicxml", fp=...), .write("midi", fp=...) or .show("text"). |
| Audio features: pitch, onsets, tempo, spectra | librosa 0.11 + soundfile |
numpy, scipy, pandas and matplotlib are installed. Use matplotlib.use("Agg"). |
miditoolkit (REMI/tokenisation-style tick data) is also available.
Rendering MIDI to audio
The only General MIDI SoundFont is /usr/share/sounds/sf2/TimGM6mb.sf2 (6 MB, basic quality). default-GM.sf2 points to it.
fluidsynth -ni -F out.wav -r 44100 /usr/share/sounds/sf2/TimGM6mb.sf2 in.mid # options before the soundfont
ffmpeg -loglevel error -y -i out.wav -q:a 2 out.mp3
- From Python,
pretty_midi.PrettyMIDI(p).fluidsynth(fs=44100)returns a mono NumPy array. Write it withsoundfile.write.
Verify by checking that the output is non-empty and has the expected duration: soundfile.info("out.wav").duration, or pm.get_end_time() for MIDI.
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.
- 15d ago First seen · 31 lines · 45 tokens per session scan A 8f42aee90bb1
midi is a skill published in the GitHub repository mazumba/opencode-dockerized (6 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 509 once invoked, about $0.0002 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 2026-10-24.
midi compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| midimazumba/opencode-dockerized | Skill | 6 | 2d ago | MIT | A | 45 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |