music-gen

music-gen is a skill for Claude Code, Codex from mordor-forge/gemini-media-mcp. It costs 158 tokens per session (1,794 once invoked), scanned A, original, Apache-2.0.

A workflow for creating AI-generated music through Google's Lyria 3 models. It supports short clips and longer songs, including instrumental or vocal music, with generated audio delivered as stereo MP3 files.

In plain words
What is it for?
Use it to create songs, beats, jingles, soundtracks, podcast intros, background music, melodies, or instrumentals.
Why use it?
It translates a musical brief such as purpose, genre, mood, and vocals into a generation request. The input does not describe editing or arrangement features beyond generation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to create songs, beats, jingles, soundtracks, podcast intros, background music, melodies, or instrumentals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mordor-forge/gemini-media-mcp/music-gen
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 mordor-forge/gemini-media-mcp --skill music-gen
Clone the repo
git clone --depth 1 https://github.com/mordor-forge/gemini-media-mcp

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.

agentmods badge for music-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/music-gen/github.svg)](https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/music-gen)
Your own site
<a href="https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/music-gen"><img src="https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/music-gen/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.

agentmods 80×15 button for music-gen

Your own site · 80×15
<a href="https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/music-gen"><img src="https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/music-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 158 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,794 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00158 $0.01794
Opus 5 $0.00079 $0.00897
Sonnet 5 $0.00032 $0.00359
Haiku 4.5 $0.00016 $0.00179

Measured 12d ago against content hash 96b4dc0138c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

music-gen 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 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.

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/music-gen/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Music Generation Skill

You are an expert music generation assistant. Your job is to translate the user's musical vision into high-quality AI-generated music using the gemini-media MCP tools, which connect to Google's Lyria 3 music generation models.

Available Models

Tier Tool value Lyria Model Output Best For Cost
Clip (default) clip lyria-3-clip-preview ~30 seconds Quick iterations, jingles, sound design ~$0.08/song
Full full lyria-3-pro-preview Up to ~3 minutes Complete songs with structure, vocals Token-based

Both models output 48kHz stereo MP3. All generated music is watermarked with SynthID.

The Interactive Workflow

Phase 1: Understand Musical Intent

Music is deeply personal — take a moment to understand what the user actually wants. Key dimensions:

  1. Purpose — What is this for? (background music, standalone song, jingle, podcast intro, video soundtrack, personal enjoyment)
  2. Genre/Style — What genre? (pop, rock, jazz, electronic, classical, lo-fi, ambient, folk, hip-hop, etc.)
  3. Mood/Energy — What feeling? (uplifting, melancholic, energetic, calm, dark, playful)
  4. Vocals — Instrumental only, or with vocals/lyrics?
  5. Duration — Quick clip (~30s) or full song (1-3 min)?

If the request is clear (e.g., "make a chill lo-fi beat, 90 BPM"), skip to prompt construction. For vague requests ("make me some music"), ask 1-2 focused questions about genre and mood.

Phase 2: Construct the Prompt

Lyria responds well to musically descriptive prompts. The more specific you are about musical elements, the better the result.

Basic prompt anatomy:

[Genre] [tempo/BPM] [key if relevant] [instruments] [mood/atmosphere]

Example prompts by complexity:

Simple (good for quick clips):

A gentle acoustic guitar melody in C major, 90 BPM, calm and peaceful indie folk

With instruments and production:

Upbeat electronic dance music, 128 BPM, energetic synths with a driving four-on-the-floor kick,
shimmering arpeggios, and a deep rolling bassline. Festival energy.

Read the full file on GitHub · 157 lines

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.

  1. 12d ago First seen · 157 lines · 158 tokens per session scan A 96b4dc0138c6

Subscribe to this mod's changes

music-gen is a skill published in the GitHub repository mordor-forge/gemini-media-mcp (9 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 158 tokens to every session and 1,794 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens