What is minimax-music?

A music-production tool for creating songs, instrumentals, lyrics, and cover-style versions from prompts, lyrics, or authorized reference audio.

Use it to make songs, background music, jingles, themes, covers, and soundtracks for videos, ads, games, and social content.

It helps turn a musical idea or reference into a usable track while keeping rights checks and production review in the workflow.

minimax-music — Skill for Claude Code and Codex by calesthio

Install

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.

Any agent

npx skills add calesthio/generative-media-skills --skill minimax-music

Clone the repo

git clone --depth 1 https://github.com/calesthio/generative-media-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/calesthio/generative-media-skills/minimax-music/github.svg)](https://agentmods.dev/skills/calesthio/generative-media-skills/minimax-music)

Your own site

<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/minimax-music"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/minimax-music"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/minimax-music.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,370 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Data Exfiltration · line 12
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Data Exfiltration · line 13
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
medium Data Exfiltration · line 14
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00053	$0.04370
Opus 5	$0.00026	$0.02185
Sonnet 5	$0.00011	$0.00874
Haiku 4.5	$0.00005	$0.00437

Measured 9d ago against content hash d23e69218e10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

minimax-music 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 9d 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.

skills/providers/music-generation/minimax-music/SKILL.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MiniMax Music production

Use MiniMax Music when the job needs an original song, instrumental bed, theme, jingle, or cover-style rendition from a style prompt, lyrics, or authorized reference audio. Treat it as a music-production provider, not a generic sound-effects tool.

The current public API surface verified on 2026-07-10 is:

POST https://api.minimax.io/v1/music_generation for text-to-music, instrumental music, and cover generation.
POST https://api.minimax.io/v1/lyrics_generation for complete lyrics or lyrics editing/continuation.
POST https://api.minimax.io/v1/music_cover_preprocess for extracting a reference track's feature ID, structured lyrics, and rough structure before an editable cover workflow.
Global docs list https://api.minimax.io; some ecosystem tooling distinguishes a China endpoint such as https://api.minimaxi.com. If authentication fails with a valid key, verify the user's account region and configured base URL rather than repeatedly retrying.

Sources verified 2026-07-10: MiniMax music guide, API reference, lyrics API reference, cover preprocess reference, rate-limit guide, pay-as-you-go pricing guide, unified terms, Audio Music Creation Terms, and privacy overview:

Route the job

Choose one of these routes before generating:

Original song with user-supplied lyrics: call music_generation with model: "music-2.6" or music-2.6-free, a production-style prompt, and the supplied lyrics.
Original song without lyrics: use lyrics_generation first, or set lyrics_optimizer: true with empty lyrics when using music-2.6/music-2.6-free. Prefer a separate lyrics pass when the words matter, because you can review structure, brand safety, and rhyme before paying for audio.
Instrumental: call music_generation with is_instrumental: true; omit lyrics. The prompt becomes mandatory and should specify genre, mood, instrumentation, energy arc, use case, and edit constraints.
Quick cover from authorized reference audio: call music_generation with model: "music-cover" or music-cover-free, audio_url or audio_base64, and a target style prompt. This extracts lyrics automatically if lyrics is omitted.
Editable cover from authorized reference audio: call music_cover_preprocess first, review/modify formatted_lyrics, then call music_generation with cover_feature_id and the edited lyrics.

Read the full file on GitHub · 297 lines

Files

What ships with it

1 file 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.

EVAL.md 9.2 KB

Changes

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.

9d ago First seen · 297 lines · 53 tokens per session scan A d23e69218e10

Subscribe to this mod's changes

minimax-music is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 4,370 once invoked, about $0.0003 per session on Opus 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 2026-09-03.

Creative and media agent agentic-ai ai ai-audio ai-video claude

cliptalk-cover-director

Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.

GML-MMGroup/ClipTalk · 53 tokens

cliptalk-smart-reframe

Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.

GML-MMGroup/ClipTalk · 58 tokens

cliptalk-content-extractor

Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.

GML-MMGroup/ClipTalk · 35 tokens

cliptalk-interview-editor

Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.

GML-MMGroup/ClipTalk · 43 tokens

cliptalk-shortform-hook-director

Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.

GML-MMGroup/ClipTalk · 48 tokens

cliptalk-social-reframe-exporter

Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…

GML-MMGroup/ClipTalk · 100 tokens