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 timoncool/ACE-Step-Studio --skill acestep-songwritinggit clone --depth 1 https://github.com/timoncool/ACE-Step-StudioWrote 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/timoncool/ace-step-studio/acestep-songwriting)<a href="https://agentmods.dev/skills/timoncool/ace-step-studio/acestep-songwriting"><img src="https://agentmods.dev/badge/skills/timoncool/ace-step-studio/acestep-songwriting/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/timoncool/ace-step-studio/acestep-songwriting"><img src="https://agentmods.dev/badge/skills/timoncool/ace-step-studio/acestep-songwriting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.02048 |
| Opus 5 | $0.00028 | $0.01024 |
| Sonnet 5 | $0.00011 | $0.00410 |
| Haiku 4.5 | $0.00006 | $0.00205 |
Grade A, and why
acestep-songwriting 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACE-Step Songwriting Guide
Professional music creation knowledge for writing captions, lyrics, and choosing music parameters for ACE-Step.
Output Format
After using this guide, produce two things for the acestep skill:
- Caption (
-c): Style/genre/instruments/emotion description - Lyrics (
-l): Complete structured lyrics with tags - Parameters:
--duration,--bpm,--key,--time-signature,--language
Caption: The Most Important Input
Caption is the most important factor affecting generated music.
Supports multiple formats: simple style words, comma-separated tags, complex natural language descriptions.
Common Dimensions
| Dimension | Examples |
|---|---|
| Style/Genre | pop, rock, jazz, electronic, hip-hop, R&B, folk, classical, lo-fi, synthwave |
| Emotion/Atmosphere | melancholic, uplifting, energetic, dreamy, dark, nostalgic, euphoric, intimate |
| Instruments | acoustic guitar, piano, synth pads, 808 drums, strings, brass, electric bass |
| Timbre Texture | warm, bright, crisp, muddy, airy, punchy, lush, raw, polished |
| Era Reference | 80s synth-pop, 90s grunge, 2010s EDM, vintage soul, modern trap |
| Production Style | lo-fi, high-fidelity, live recording, studio-polished, bedroom pop |
| Vocal Characteristics | female vocal, male vocal, breathy, powerful, falsetto, raspy, choir |
| Speed/Rhythm | slow tempo, mid-tempo, fast-paced, groovy, driving, laid-back |
| Structure Hints | building intro, catchy chorus, dramatic bridge, fade-out ending |
Caption Writing Principles
- Specific beats vague — "sad piano ballad with female breathy vocal" > "a sad song"
- Combine multiple dimensions — style+emotion+instruments+timbre anchors direction precisely
- Use references well — "in the style of 80s synthwave" conveys complex aesthetic quickly
- Texture words are useful — warm, crisp, airy, punchy influence mixing and timbre
- Don't pursue perfection — Caption is a starting point, iterate based on results
- Granularity determines freedom — Less detail = more model creativity; more detail = more control
- Avoid conflicting words — "classical strings" + "hardcore metal" degrades output
- Fix: Repetition reinforcement — Repeat the elements you want more
- Fix: Conflict to evolution — "Start with soft strings, middle becomes metal rock, end turns to hip-hop"
- Don't put BPM/key/tempo in Caption — Use dedicated parameters instead
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 · 195 lines · 55 tokens per session scan A c510cd4242df
acestep-songwriting is a skill published in the GitHub repository timoncool/ACE-Step-Studio (340 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 2,048 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 skills, from other repositories
claude-music
Music production suite using ACE-Step 1.5 via Python API. Routes /music commands for generation, cover, repaint, compose, analyze, export, enhance, random, and LoRA training. 50+ languages, up to 10-minute tracks, 48kHz stereo.
claude-music-cover
Creates cover versions and style transfers of existing songs using ACE-Step 1.5. Takes a reference audio file and generates a new version with different style, genre, or vocal characteristics while preserving musical structure.
claude-music-enhance
Post-processing for generated music. Default path is FFmpeg loudness normalization (fast, CPU-only). Escape hatches: AI vocal denoise for artifacts, stem separation for surgical edits. Both escape-hatch paths reuse tooling from the claude-video skill.
claude-music-lora
LoRA and LoKr fine-tuning for ACE-Step 1.5. Trains custom styles from 3-10 songs, manages trained adapters, and applies them during generation. Uses ACE-Step's built-in training pipeline.
claude-music-repaint
Edits specific sections of a song using ACE-Step 1.5's repaint mode. Fixes a bad chorus, changes instruments in a section, adds or removes vocals, or regenerates any time range while keeping the rest intact.
claude-music-analyze
Analyzes audio files for BPM, musical key, loudness (LUFS), duration, format, and quality metrics. Uses ffprobe for metadata and FFmpeg for loudness measurement.