song-critic

song-critic is a skill for Claude Code from P47Phoenix/Claude-Plugins. It costs 142 tokens per session (2,745 once invoked), scanned A, original, MIT.

A songwriting critic that evaluates songs using separate judges for areas such as hooks, rhythm, music, structure, adaptation, and listener response. It also uses an independent challenger to test the final work in a clean context.

In plain words
What is it for?
It detects the requested judging role, sends the relevant material and rubric to a separate agent, and returns critiques, panel reports, or challenge reports.
Why use it?
It separates creation from evaluation, so the critic does not rewrite the song or approve its own work. Its reports explain problems and rank possible fixes.

Skill for Claude Code

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

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

Good fit It detects the requested judging role, sends the relevant material and rubric to a separate agent, and returns critiques, panel reports, or challenge reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/p47phoenix/claude-plugins/song-critic
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 song-critic
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 song-critic

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/song-critic"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/song-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,745 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 $0.00142 $0.02745
Opus 5.5 $0.00057 $0.01098
Sonnet 5.5 $0.00028 $0.00549
Haiku 4.5 $0.00014 $0.00275

Measured 2d ago against content hash 77bf81082287, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

song-critic 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/song-critic/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Song Critic

Design Principle: Role Context Isolation

Keep judging knowledge out of the main context. Detect the role, read only the matched role manifest, its contract and the rubric or personas it names, then spawn a sub-agent that does the judging. The main context receives the critique, panel report or challenge report and a hand-back, never the rubrics. Paste the fenced clause of references/shared/originality-policy.md verbatim under <!-- originality-policy --> in every prompt.

A critic is never the worker's agent instance, never rewrites an artifact, and never overrides a gate: the script decides, the critic explains and ranks fixes.


Phase 1: Role Detection

Detect the role from, in priority order:

  1. Pipeline invocation. A prompt that begins with SKILL: song-critic carries ROLE: and TASK_TYPE:. Honour them and skip detection. Template 3 passes TASK_TYPE: critique for every judge; map it to the role's task type below.
  2. Explicit role mention. "as the challenger", "ask the panel".
  3. Task signals. See the routing table.
  4. Artifact signals. A supplied challenge-report.md or adaptation-report.md with no other cue routes to the challenger or the fidelity judge respectively. Several artifacts and "is it any good" means a panel.

If ambiguous, ask one question before proceeding. Example: "judge this" with lyrics and chords could mean the prosody or music judge.

Declare before every task:

Role: [ROLE] | Task: [TASK_TYPE] | References: [list of reference files]

Role Routing Table

Load only the matched manifest. Each holds the task-type routing table, instructions and guardrails.

Role Manifest Task type Stage Detection cue
Hook Judge references/roles/judges.md critique 2 judge the hook, title strength, hook line
Prosody Judge references/roles/judges.md critique 4 review my lyrics, judge the chorus, stress, rhyme, prosody check
Music Judge references/roles/judges.md critique 5 chords, melody, singability review
Structure Judge references/roles/judges.md critique 3, 6 structure, arrangement, energy map review
Adaptation Fidelity references/roles/adaptation-fidelity.md fidelity-review 7p how faithful is this adaptation, kept vs changed, meaning drift
Listener Panel references/roles/listener-panel.md panel 7a listener panel, listener feedback, would people like this
Challenger references/roles/challenger.md challenge 7b challenge this song, is this original, cliche hunt, resemblance

Read the full file on GitHub · 235 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. 2d ago First seen · 235 lines · 142 tokens per session scan A 77bf81082287

Subscribe to this mod's changes

song-critic is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 142 tokens to every session and 2,745 once invoked, about $0.0006 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.

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