agentmods.dev

music-brief

music-brief is a skill for Claude Code from P47Phoenix/Claude-Plugins. It costs 95 tokens per session (2,421 once invoked), scanned A, original, MIT.

A songwriting intake guide that turns a short request into a defined song type and a brief. It asks only for missing information and refuses some requests, such as parody or named-artist requests.

In plain words
What is it for?
It detects one of the supported song types, gathers required details, and writes the brief and run configuration without writing song lyrics or music.
Why use it?
It prevents the song-making process from starting with an unclear brief or the wrong workflow. It also checks source information for adaptation and lyric-extension requests.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the music-team plugin — 9 skills shipped together

not rated 2repo 2d ago A scan 95 tokens original MIT

Good fit It detects one of the supported song types, gathers required details, and writes the brief and run configuration without writing song lyrics or music.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/p47phoenix/claude-plugins/music-brief
View source ↗ P47Phoenix/Claude-Plugins
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 P47Phoenix/Claude-Plugins --skill music-brief
Clone the repo
git clone --depth 1 https://github.com/P47Phoenix/Claude-Plugins

Made for: Claude Code.

Or install music-team, the plugin that ships this one along with the rest of its 9 skills.

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-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/music-brief/github.svg)](https://agentmods.dev/skills/p47phoenix/claude-plugins/music-brief)
Your own site
<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/music-brief"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/music-brief/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-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/music-brief"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/music-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,421 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 $0.00095 $0.02421
Opus 5.5 $0.00038 $0.00968
Sonnet 5.5 $0.00019 $0.00484
Haiku 4.5 $0.00010 $0.00242

Measured 2d ago against content hash 46d4006cb3d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

music-brief 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 2d 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.

music-team/skills/music-brief/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

music-brief

Design Principle

Intake runs inline and writes only brief.md, .song/config.yml (when absent), and .song/active. It never writes song content: no title, hook, lyric, or chord. Song type is a per-run decision, not a project setting. Routing lives in music-team/references/shared/song-types.md; this skill detects the type and hands the declaration to music-flow. Per-type required keys: music-team/skills/music-brief/references/intake-keys.md.

Phase 1: Song Type Detection

Detection is cheap pattern work; run it on the phase_1_detector_model (haiku) when delegated. Walk the rows of song-types.md in priority order and stop at the first match:

PARODY_ADAPT, REVISE, THEORY, ADAPT_GENRE, AUGMENT_LYRICS, REWRITE, TOPLINE, INSTRUMENTAL, JINGLE, LYRICS_ONLY, FULL_SONG (default).

Steps

  1. Read config. Read .song/config.yml if present. When absent, copy music-team/.song.config.yml.example to .song/config.yml and announce it. (mkdir -p .song first.)
  2. Explicit override. When routing.force_type is set, detection still runs and its result is logged, but routing uses the pin. Announce on every run: FORCED TYPE: <pin> (detected: <T>). REVISE is never forced; a force_type of REVISE is ignored with a one-line warning.
  3. PARODY_ADAPT first. Signals: "parody", "to the tune of", "in the style of ", "like 's song", or a references/shared/blocked-targets.txt entry (whole phrase, case-insensitive) used as a target. "In the style of " is not a signal. On a match reply with the refusal sentence below and stop (see Refusal).
  4. REVISE only with a finished run. Read .song/active; if it names a slug whose .song/<slug>/state.json has status: complete and the request is a change ("make the chorus punchier", "change the key", "swap verse two"), the type is REVISE. With no finished run, ignore the REVISE row and continue down the list.
  5. Remaining rows in order: THEORY (question about a progression, mode, cadence, no song deliverable), ADAPT_GENRE (supplied lyric or chords plus a target genre), AUGMENT_LYRICS (supplied lyric plus "add a verse", "bridge", "extend"), then REWRITE, TOPLINE, INSTRUMENTAL, JINGLE, LYRICS_ONLY, FULL_SONG. Apply the reducers from song-types.md: ADAPT_GENRE with no supplied source becomes FULL_SONG in that genre; AUGMENT_LYRICS with only "fix/tighten/polish" becomes REWRITE.
  6. Ambiguity. When two rows tie after the reducers, ask one question naming both candidates ("Do you want me to write new material, or adapt the lyric you pasted?") and re-run steps 3-5 on the answer. Do not guess between a creative type and a refusal.

Read the full file on GitHub · 167 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.

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. 2d ago First seen · 167 lines · 95 tokens per session scan A 46d4006cb3d4

Subscribe to this mod's changes

music-brief is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 2,421 once invoked, about $0.0004 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 2026-10-26.

Creative and media
Related

Other skills, from other repositories

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

systematic-debugging

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

obra/superpowers · 21 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