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.
npx skills add P47Phoenix/Claude-Plugins --skill composergit clone --depth 1 https://github.com/P47Phoenix/Claude-PluginsWrote 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.
[](https://agentmods.dev/skills/p47phoenix/claude-plugins/composer)<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/composer"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/composer/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.
<a href="https://agentmods.dev/skills/p47phoenix/claude-plugins/composer"><img src="https://agentmods.dev/badge/skills/p47phoenix/claude-plugins/composer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00149 | $0.02795 |
| Opus 5.5 | $0.00060 | $0.01118 |
| Sonnet 5.5 | $0.00030 | $0.00559 |
| Haiku 4.5 | $0.00015 | $0.00280 |
Grade A, and why
composer 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composer Agent
Design Principle: Role Context Isolation
This skill keeps music-theory and notation knowledge out of the main context window. When a composing task arrives, the role is detected, only the matching role manifest, its output contract, the genre sections the role needs, and a few theory or technique files are read, and a sub-agent is spawned with that isolated context. The main context receives only the finished artifact path (or, for theory questions, the finished inline answer).
Four roles share this skill: harmony writes chords.md, melody writes melody.abc, groove writes structure.md, theorist answers theory questions inline. They never share a prompt: one role is one Agent call.
Phase 1: Role Detection
Pipeline mode. When the prompt begins SKILL: composer, a TASK_TYPE: and a ROLE: line are given by the orchestrator (music-flow). Honour them. Do not detect. Begin the output with SKILL_LOADED: <every references/ path embedded>.
Standalone mode. Detect the role from (in priority order):
- Explicit role mention -- "as the harmony writer", "theory question", "just the melody"
- Deliverable signals -- see the role manifests below
- Domain signals -- chord and numeral words route to harmony; ABC, topline, motif, singable words to melody; key, tempo, meter, form, section-length words to groove; "explain", "analyze", "why", "what mode", "what fits" to theorist
- Artifact signals -- a supplied progression to explain, or a request for reharmonization options (answer only, written inline), routes to theorist; a request to write or revise
chords.md(reharmonize a section in the artifact) routes to harmony
If ambiguous, ask before proceeding. Do not assume.
Standalone use outside a .song/ run prints one line first: Note: no active pipeline (no .song/active); working standalone, nothing is gate-checked by the orchestrator. Then proceed.
Declare before every task:
Role: [ROLE] | Task: [TYPE] | References: [list of reference files]
What ships with it
19 files 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.
- references/contracts/cross-role-tasks.md 3.4 KB
- references/contracts/harmony-output.md 3.4 KB
- references/contracts/melody-output.md 3.2 KB
- references/contracts/structure-output.md 3.8 KB
- references/contracts/theory-output.md 3.8 KB
- references/roles/groove.md 4.0 KB
- references/roles/harmony.md 4.7 KB
- references/roles/melody.md 3.8 KB
- references/roles/theorist.md 4.6 KB
- references/techniques/abc-notation-primer.md 3.1 KB
- references/techniques/borrowed-chords.md 2.9 KB
- references/techniques/melodic-contour.md 3.1 KB
- references/techniques/modal-color.md 2.9 KB
- references/techniques/rhythmic-feel.md 3.2 KB
- references/theory/form-and-meter.md 3.5 KB
- references/theory/functional-harmony.md 3.3 KB
- references/theory/modes-scales.md 3.1 KB
- references/theory/reharmonization.md 3.6 KB
- references/theory/voice-leading.md 3.2 KB
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.
- 2d ago First seen · 230 lines · 149 tokens per session scan A c7e7f17b810c
composer is a skill published in the GitHub repository P47Phoenix/Claude-Plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 149 tokens to every session and 2,795 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.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…