musica

musica is a skill for Claude Code from inhabitants/sapiens-mcp. It costs 55 tokens per session (808 once invoked), scanned A, original, MIT.

A workflow for creating a complete song or a short sound effect with the Musicator tools. A song is created, given lyrics, rendered into audio, and checked until it is ready; sound effects use a separate process.

In plain words
What is it for?
Use it to draft and render songs, poll their completion status, publish finished tracks to the community collection, or generate short sound effects.
Why use it?
It prevents failed requests caused by skipping required steps or confusing a full song with a short effect. It also explains how to find an existing free sound effect before generating one.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sapiens-sinteticos plugin — 18 skills, 1 MCP server shipped together

Good fit Use it to draft and render songs, poll their completion status, publish finished tracks to the community collection, or generate short sound effects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/inhabitants/sapiens-mcp/musica
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 inhabitants/sapiens-mcp --skill musica
Clone the repo
git clone --depth 1 https://github.com/inhabitants/sapiens-mcp

Made for: Claude Code.

Or install sapiens-sinteticos, the plugin that ships this one along with the rest of its 18 skills, 1 MCP server.

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 musica

README.md
[![agentmods](https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/musica/github.svg)](https://agentmods.dev/skills/inhabitants/sapiens-mcp/musica)
Your own site
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/musica"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/musica/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 musica

Your own site · 80×15
<a href="https://agentmods.dev/skills/inhabitants/sapiens-mcp/musica"><img src="https://agentmods.dev/badge/skills/inhabitants/sapiens-mcp/musica.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 808 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 $0.00055 $0.00808
Opus 5.5 $0.00022 $0.00323
Sonnet 5.5 $0.00011 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 4d ago against content hash 686d5cb9dc52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

musica 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 4d 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.

plugins/sapiens-sinteticos/skills/musica/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Música e efeito sonoro

Musicator: 4 passos, nesta ordem

  1. create: exige title (>=3 chars) e context (>=20 chars, o tema/ângulo) e direction (gênero/mood). Custo 0. Devolve trackId.
  2. lyrics: passe trackId e context pra gravar a letra na track (300 Sinapses). Nunca chame lyrics sem title e context.
  3. render: passe o trackId pronto pra sintetizar o áudio (3000 Sinapses, assíncrono, teto de 3/min).
  4. get: passe o trackId e vá polando o status até 'ready' (ou 'failed').

Qual motor no render

model escolhe o motor. Sem ele, sai no Lyria 3.5.

  • pro: Lyria 3.5, faixa inteira até 3 min. Único que lê imagem de referência.
  • clip: Lyria 3 Clip, rascunho de 30s pra testar a ideia.
  • mureka: Mureka 9.5, faixa inteira, aguenta letra de até 5.000 caracteres.
  • minimax: MiniMax Music 2.6, faixa inteira até 5 min. Letra de 10 a 3.000 caracteres.
  • elevenlabs: ElevenLabs Music, a pessoa escolhe a duração em durationSeconds (30, 60, 120 ou 180; sem ele, 120). Letra até 3.500 caracteres.

Todos custam o mesmo render fixo, menos o ElevenLabs, que cobra pela duração (durationSeconds): 30s 1300, 60s 2550, 120s 5050, 180s 7600 Sinapses. Diga o número e confirme antes de disparar o de 3 min.

Letra maior que o teto do motor é recusada ANTES de cobrar, com o tamanho na mensagem: corte a letra ou troque de motor. negativePrompt e seed só valem no Lyria.

Pular pro lyrics ou render sem create, ou sem os campos, falha sempre. É o erro número um deste fluxo.

Depois de pronta: action=publish põe a faixa no Acervo da Comunidade (só admin/dono, custo 0, idempotente). A publicação já nasce com player no Fórum, veja a skill forum.

Efeito sonoro é outra coisa

Efeito é CURTO. Música inteira é no Musicator, não aqui.

  1. Procure pronto primeiro: sapiens_stock_audio action=list kind=sfx. Grátis.
  2. Não achou: action=generate com prompt e durationSeconds (1 a 15, default 5) e provider ('mirelo' padrão 35 Sinapses/s mín 70, 'elevenlabs' premium 60/s mín 120). promptInfluence (0..1) só vale no elevenlabs.
  3. É assíncrono: devolve generationId, acompanhe com action=generation-status até 'ready' (traz audioUrl) ou 'failed' (reembolsa sozinho).

Read the full file on GitHub · 44 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. 4d ago Changed · +14 lines 686d5cb9dc52
  2. 26d ago First seen · 30 lines · 55 tokens per session scan A 0e2f4b66a44d

Subscribe to this mod's changes

musica is a skill published in the GitHub repository inhabitants/sapiens-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 808 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 2026-09-28.

Related

Other skills, from other repositories

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…

comet-ml/opik-mcp · 187 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

dcc-blender-assembly-pitfalls

Read this BEFORE writing any Blender geometry code through MCP, whenever you are about to (1) create or size mesh primitives - bpy.ops.mesh.primitivecubeadd, primitivecylinderadd, primitiveuvsphereadd, primitiveconeadd - or set scale / dimensions on a part; (2) orient a part with rotationeuler or rotationquaternion…

dcc-mcp/dcc-mcp-blender · 153 tokens

linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

jmagar/claude-homelab · 69 tokens

split-to-prs

Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

Kevin-Liu-01/Agent-Machines · 34 tokens

quantum-algorithms

A routing workflow for choosing an open-source quantum-computing algorithm and loading the matching local workflow. Quantum computing uses circuits and quantum states to represent and process information.

xi-zhao/OpenQuantum · 34 tokens