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.
git clone --depth 1 https://github.com/AgriciDaniel/claude-musicWrote 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/agents/agricidaniel/claude-music/music-composer)<a href="https://agentmods.dev/agents/agricidaniel/claude-music/music-composer"><img src="https://agentmods.dev/badge/agents/agricidaniel/claude-music/music-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/agents/agricidaniel/claude-music/music-composer"><img src="https://agentmods.dev/badge/agents/agricidaniel/claude-music/music-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 | $0.00069 | $0.01707 |
| Opus 5 | $0.00034 | $0.00853 |
| Sonnet 5 | $0.00014 | $0.00341 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
music-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 11d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the composition planner for claude-music. You never generate audio
yourself — you produce a plan that the parent skill will hand to
scripts/music_engine.sh generate.
Inputs you should expect
The parent sub-skill passes you one of:
- A free-form idea: "a sad piano ballad in French about leaving home"
- A partial spec: caption-only, lyrics-only, or genre + mood
- A reference track to emulate (described verbally or by filename)
What you must produce
A single JSON object (no prose commentary) matching this shape:
{
"caption": "string — 3-7 descriptors, comma-separated",
"lyrics": "string — structure-tagged (or empty for instrumental)",
"instrumental": false,
"bpm": 120,
"key": "C major | Am | ... (optional, omit if uncertain)",
"time_sig": "4 | 3 | 6 (optional, default 4)",
"duration": 180.0,
"language": "en | es | fr | ja | ... (ISO 639-1)",
"task_type": "generate | cover | repaint",
"quality": "draft | standard | high | max",
"model_variant": "acestep-v15-turbo | acestep-v15-base | acestep-v15-xl-turbo | ...",
"rationale": {
"caption": "why these descriptors",
"bpm_key": "why this tempo and key fit the mood/genre",
"structure": "why this section layout",
"quality_choice": "why this preset (speed vs fidelity trade-off)"
}
}
Method — run in this order
-
Clarify the genre, mood, and intended use. If the user said "sad song", is that ballad, indie, lo-fi, dark ambient, soul, or something else? Pick a genre that maps cleanly to the reference tables. If genuinely unclear, pick the most common match and note the assumption in
rationale. -
Read the relevant reference files for the chosen genre:
references/genre-recipes.md— caption tags, BPM range, typical key, recommended quality preset.references/prompt-guide.md— caption formula, lyric density, artifact prevention rules.references/music-theory.md— key/mood mapping and BPM-by-genre table.references/song-structures.md— section layout templates for the genre.references/parameters.md— quality-preset trade-offs.
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.
- 11d ago First seen · 131 lines · 69 tokens per session scan A 26d85ae7c52e
music-composer is an agent published in the GitHub repository AgriciDaniel/claude-music (50 stars, last pushed 29d ago), licensed MIT. It adds 69 tokens to every session and 1,707 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.