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 joeVenner/awesome-minimax-h3 --skill minimax-musicgit clone --depth 1 https://github.com/joeVenner/awesome-minimax-h3Wrote 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/joevenner/awesome-minimax-h3/minimax-music)<a href="https://agentmods.dev/skills/joevenner/awesome-minimax-h3/minimax-music"><img src="https://agentmods.dev/badge/skills/joevenner/awesome-minimax-h3/minimax-music/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/joevenner/awesome-minimax-h3/minimax-music"><img src="https://agentmods.dev/badge/skills/joevenner/awesome-minimax-h3/minimax-music.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 | $0.00180 | $0.04408 |
| Opus 5 | $0.00090 | $0.02204 |
| Sonnet 5 | $0.00036 | $0.00882 |
| Haiku 4.5 | $0.00018 | $0.00441 |
Grade A, and why
minimax-music scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Requires a MiniMax platform API key (https://platform.minimax.io), curl, jq, and ffmpeg for post-processing How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax Music — Cloud Music Generation
This skill covers the CLOUD platform API only (api.minimax.io, Bearer auth with a platform
API key). It does not cover the local Electron gateway — see minimax-local-audio for that, and
do not mix their parameter shapes: this API takes real JSON types ("is_instrumental": true),
the local gateway takes strings ("is_instrumental": "instrumental").
Quick start — instrumental bed
curl -s -X POST "https://api.minimax.io/v1/music_generation" \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "music-3.0",
"is_instrumental": true,
"prompt": "Cinematic indie folk, warm, nostalgic, hopeful, felt piano, soft string swell, slow tempo, 76 BPM",
"audio_setting": {"sample_rate": 44100, "bitrate": 256000, "format": "mp3"},
"output_format": "url"
}' -o resp.json
jq -r '.data.audio' resp.json | xargs curl -sL -o track.mp3
⏱ Generation takes ~3 minutes and the call blocks the whole time. Set a client timeout of at least 600s and run it in the background. A 120s shell timeout will kill it mid-flight.
✅ Verified facts that contradict older documentation
| Older claim | Reality (verified 2026-08-04) |
|---|---|
| Output is ~25 seconds | ~161 seconds measured. The "25364" in the docs is an example value, not a limit |
| Audio returns as hex only | output_format: "url" returns a signed download URL in data.audio |
data.audio is a separate field from any URL |
Same field carries either hex or the URL, depending on output_format |
Only music-3.0 and music-cover exist |
Six models exist, including free-tier variants |
There is still no duration parameter and no way to place a climax at a chosen timestamp. Output length is emergent — but it is long, so for anything under ~2 minutes the practical approach is: generate, measure, then trim and fade to fit in ffmpeg.
Phase 0: The brief
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.
- 12d ago First seen · 366 lines · 0 tokens per session scan A 24cbd7d8e55e
minimax-music is a skill published in the GitHub repository joeVenner/awesome-minimax-h3 (9 stars, last pushed 27d ago), licensed MIT. It adds 180 tokens to every session and 4,408 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
flux-analyzer
Analyse FBA flux distributions to extract biological insights. Covers gene essentiality, phenotypic phase planes, flux sampling, pathway-level aggregation, secretion product prediction, and production of publication- quality figures.
statistical-method-design
Design statistical methods, baselines, diagnostics, variants, and ablations that directly address a formal problem formulation.
experimental-design
Best practices for designing reproducible ML experiments. Use when planning ablations, baselines, or controlled experiments.
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
proof-derivation-forensics
Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation …
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.