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 PerIPan/music-workflow-skills --skill song-analysisgit clone --depth 1 https://github.com/PerIPan/music-workflow-skillsWrote 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/peripan/music-workflow-skills/song-analysis)<a href="https://agentmods.dev/skills/peripan/music-workflow-skills/song-analysis"><img src="https://agentmods.dev/badge/skills/peripan/music-workflow-skills/song-analysis/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/peripan/music-workflow-skills/song-analysis"><img src="https://agentmods.dev/badge/skills/peripan/music-workflow-skills/song-analysis.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 | $0.00055 | $0.04376 |
| Opus 5.5 | $0.00022 | $0.01750 |
| Sonnet 5.5 | $0.00011 | $0.00875 |
| Haiku 4.5 | $0.00006 | $0.00438 |
Grade A, and why
song-analysis 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 1mo 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Song Analysis — recording → bars, chords, lyrics, chart
Song-agnostic pipeline, validated over many real projects (dream pop, Greek laiko, punk reinterpretations, drone/devotional). Works for any song, genre, key or meter.
References (read on demand):
references/meter-detection.md— how the meter sweep works, reading its output, calibrationreferences/stems.md— separation options, speeds, cache, quality checksreferences/chord-proposal.md— chord benchmark, the triad cross-check, the major-bias trapreferences/chart-and-lyrics.md— chart structure, the lyric-placement rules, HTML outputreferences/drum-pattern-analysis.md— kick/snare pattern reading; optional ADTOFreferences/modal-theory.md— the 7 modes and the mode test, power chords, Byzantine ≠ Phrygianreferences/lead-and-keys-extraction.md— isolated guitar/piano lines viahtdemucs_6sreferences/environment-setup.md— venvs, pinned versions, folder layout, this machine
Inputs
- Audio file — mp3/wav of the song (full mix).
- Lyrics — canonical text from an official source. Section labels (Verse, Chorus, Bridge…) come from this, not from the analyzer.
Tool per step
| Phase | Tool | Output |
|---|---|---|
| 1 Pulse + key | scripts/foundation.py pulse (madmom beats + CNN key) |
foundation.json (step 1) |
| 2 Stems | demucs htdemucs_ft -d mps |
stems/htdemucs_ft/<song>/ |
| 3 Meter | scripts/detect_meter.py → scripts/foundation.py meter |
meter.json, foundation.json (step 2) |
| 4 Bass, tonic, mode | scripts/bass_notes.py (pyin) → scripts/mode_test.py |
bass.mid, bass_per_cell.json, mode.json |
| 5 Lyrics | scripts/whisper_gated.py (gated by the vocal stem; stem and mix) |
lyrics.json, lyrics_mix.json |
| 6 Sections | scripts/align_lyrics.py (canonical lyrics ↔ word times) |
lyrics_aligned.json, sections.json |
| 7 Chords | scripts/lv_chords.py, cross-checked by scripts/chord_proposal.py |
chords_lv.json, chord_proposal.json |
| 8 Chart | Python → self-contained HTML | chart |
What ships with it
23 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.
- bench/run_bench.py 9.7 KB runs code
- references/chart-and-lyrics.md 8.4 KB
- references/chord-proposal.md 5.9 KB
- references/drum-pattern-analysis.md 7.4 KB
- references/environment-setup.md 7.1 KB
- references/lead-and-keys-extraction.md 2.5 KB
- references/meter-detection.md 7.9 KB
- references/modal-theory.md 4.7 KB
- references/stems.md 2.8 KB
- scripts/align_lyrics.py 8.7 KB runs code
- scripts/bass_notes.py 4.7 KB runs code
- scripts/chord_proposal.py 7.8 KB runs code
- scripts/detect_meter.py 17 KB runs code
- scripts/foundation.py 11 KB runs code
- scripts/lv_chords.py 5.7 KB runs code
- scripts/mode_test.py 7.1 KB runs code
- scripts/validate_artifacts.py 4.8 KB runs code
- scripts/whisper_gated.py 4.4 KB runs code
- tests/test_align_lyrics.py 3.1 KB runs code
- tests/test_chord_proposal.py 2.7 KB runs code
- tests/test_detect_meter.py 3.2 KB runs code
- tests/test_foundation.py 2.7 KB runs code
- tests/test_mode_test.py 2.5 KB runs code
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.
- 1mo ago Changed · -68 lines · -23 tokens per session c7c40ef108b4
- 1mo ago Changed · -1 lines 9fee1819d291
- 2mo ago First seen · 355 lines · 78 tokens per session scan A 53398bc143da
song-analysis is a skill published in the GitHub repository PerIPan/music-workflow-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 4,376 once invoked, about $0.0002 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 2026-08-31.
song-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| song-analysisPerIPan/music-workflow-skills | Skill | 3 | 1mo ago | MIT | A | 55 | Claude Code, Codex |
| imaging-data-commonsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 73 | Claude Code, Codex |
| lab-hardware-cadK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 108 | Claude Code |
| statistical-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 111 | Claude Code, Codex |
| biopythonK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 65 | Claude Code |
| neuropixels-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 99 | Claude Code, Codex |
| onekgpdK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 143 | Claude Code |