What is claude-music CLAUDE.md?

A set of instructions for using Claude Code as an AI music-production tool with ACE-Step 1.5, a music-generation system.

Creating, editing, analysing, enhancing, exporting, and organising generated music, plus training LoRA models, which are small customisation models.

It gives the coding agent the project layout, operating rules, and setup details needed to work with the music tool.

How AgriciDaniel/claude-music configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AgriciDaniel/claude-music. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AgriciDaniel/claude-music/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/AgriciDaniel/claude-music

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/agricidaniel/claude-music/claude-md/github.svg)](https://agentmods.dev/instructions/agricidaniel/claude-music/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/agricidaniel/claude-music/claude-md"><img src="https://agentmods.dev/badge/instructions/agricidaniel/claude-music/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/agricidaniel/claude-music/claude-md"><img src="https://agentmods.dev/badge/instructions/agricidaniel/claude-music/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,472 This file is loaded in full into every session.

When invoked 1,472 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01472	$0.01472
Opus 5	$0.00736	$0.00736
Sonnet 5	$0.00294	$0.00294
Haiku 4.5	$0.00147	$0.00147

Measured 10d ago against content hash 78368b8a6132, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-music CLAUDE.md 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 10d 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.

CLAUDE.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-music

AI music production skill for Claude Code, powered by ACE-Step 1.5.

Project Structure

claude-music/
├── install.sh              # Interactive installer (handles ACE-Step + models + config)
├── uninstall.sh            # Removes symlinks only
├── skills/
│   ├── claude-music/       # Main orchestrator
│   │   ├── SKILL.md        # Command routing, safety rules, VRAM tiers
│   │   ├── config.json     # ACE-Step path + generation defaults
│   │   ├── scripts/        # 7 executable scripts (bash + python)
│   │   └── references/     # 7 on-demand knowledge docs
│   ├── claude-music-generate/   # text2music
│   ├── claude-music-cover/      # style transfer
│   ├── claude-music-repaint/    # section editing
│   ├── claude-music-compose/    # songwriting guide
│   ├── claude-music-export/     # platform export
│   ├── claude-music-analyze/    # BPM/key/loudness
│   ├── claude-music-enhance/    # post-processing
│   ├── claude-music-random/     # quick random gen
│   ├── claude-music-library/    # output management
│   └── claude-music-lora/       # LoRA training

How It Works

Direct Python API — Scripts import acestep directly via sys.path.insert, invoked with uv run from the ACE-Step directory. No REST API server needed.
Symlink installation — install.sh creates symlinks from ~/.claude/skills/claude-music* to this repo's skills/ directory. Edit here, changes are live.
JSON output — All scripts output structured JSON to stdout. Progress/debug goes to stderr. Claude parses the JSON for file paths, seeds, and timing.
Config-driven — config.json is the single source of truth for the ACE-Step path. All scripts read from it; no hardcoded paths in code.
Output naming — generate_music() writes its own UUID filenames, so rename_outputs() runs after generation in each cmd_* and renames in place to slug_date_index_seed.ext. It never overwrites (appends -2), keeps meaningful stems like vocals, and logs-and-continues if a rename fails. slugify() is also the basename sanitizer: only [a-z0-9-] survives a caption. Disable with --naming uuid.
Settings precedence — CLI flag > config.json > quality preset. build_parser() seeds --quality, --format, --language and --output-dir from config; resolve_quality() applies the same chain to the preset-owned keys. Preset-owned keys (model, lm_model, batch_size, thinking) are omitted from the shipped config on purpose — setting one pins it across every preset.

Read the full file on GitHub · 99 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.

10d ago First seen · 99 lines · 1,472 tokens per session scan A 78368b8a6132

Subscribe to this mod's changes

claude-music CLAUDE.md is an instructions file published in the GitHub repository AgriciDaniel/claude-music (50 stars, last pushed 28d ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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.

Claude Code Creative and media ace-step ai-music claude music-generation skill

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-music: Instructions file for Claude Code