Borrowing it
Nothing to install: this file belongs to tskovlund/mcp-score. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tskovlund/mcp-score/main/.claude/skills/score-generate/SKILL.mdgit clone --depth 1 https://github.com/tskovlund/mcp-scoreWrote 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/tskovlund/mcp-score/score-generate)<a href="https://agentmods.dev/skills/tskovlund/mcp-score/score-generate"><img src="https://agentmods.dev/badge/skills/tskovlund/mcp-score/score-generate/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/tskovlund/mcp-score/score-generate"><img src="https://agentmods.dev/badge/skills/tskovlund/mcp-score/score-generate.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 | $0.00074 | $0.02478 |
| Opus 5.5 | $0.00030 | $0.00991 |
| Sonnet 5.5 | $0.00015 | $0.00496 |
| Haiku 4.5 | $0.00007 | $0.00248 |
Grade A, and why
score-generate 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score Generation
Generate music scores by writing and executing music21 Python scripts that export MusicXML.
Instructions
- Understand the request — identify: instrumentation, key, time signature, tempo, form/structure, chord progressions, specific notation elements.
- Gather missing metadata — if the user hasn't specified title, composer, arranger, or other relevant details, ask them before generating. Only skip asking if the user explicitly says to use defaults or not to ask. Relevant metadata includes:
- Title (required — ask if not provided)
- Composer (ask if not provided)
- Arranger (ask if applicable, e.g. arrangements, charts)
- Subtitle (ask if the piece has a descriptive subtitle, genre, or dedication)
- Copyright (ask if the user wants a copyright notice)
- Write a complete Python script using music21 that builds the entire score. Save it to a temporary file (for example
/tmp/generate_score.py, or under%TEMP%on Windows). - Execute the script from the folder where the score should land. The script writes
<Title>.musicxmlinto the working directory:cd ~/Desktop && mcp-score run /tmp/generate_score.py - Report the output file path. The user opens it in MuseScore.
Default output location: ~/Desktop/<Title>.musicxml unless the user names another folder.
Critical Conventions
Flat and Sharp Notation
music21 uses - for flats in note names, key names, and chord symbol roots. This is the most common source of bugs:
# WRONG — "Bb7" is parsed as B root with a b7 alteration, NOT Bb dominant 7th
harmony.ChordSymbol("Bb7") # B major + flat-7 — wrong!
# CORRECT — use '-' for flats in the root
harmony.ChordSymbol("B-7") # Bb dominant 7th
harmony.ChordSymbol("E-7") # Eb dominant 7th
harmony.ChordSymbol("A-maj7") # Ab major 7th
harmony.ChordSymbol("D-9") # Db dominant 9th
# Sharps use '#' as expected in roots
harmony.ChordSymbol("F#m7") # F# minor 7th
harmony.ChordSymbol("C#7") # C# dominant 7th
# In extensions/alterations, 'b' and '#' work normally
harmony.ChordSymbol("Cm7b5") # C half-diminished
harmony.ChordSymbol("Cmaj7#11") # C major 7 sharp 11
harmony.ChordSymbol("G7b9") # G dominant 7 flat 9
harmony.ChordSymbol("C7#5") # C augmented dominant 7
What ships with it
2 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.
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 · -5 lines 3f79058c92b7
- 2mo ago Changed · +3 lines c10211fe55dd
- 2mo ago First seen · 231 lines · 74 tokens per session scan A 7b020fd0091f
score-generate is a skill published in the GitHub repository tskovlund/mcp-score (32 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 2,478 once invoked, about $0.0003 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 2026-08-30.
score-generate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| score-generatetskovlund/mcp-score | Skill | 32 | 6d ago | MIT | A | 74 | Claude Code |
| musescore-drum-chartghchen99/mcp-musescore | Skill | 140 | yesterday | MIT | A | 159 | Claude Code, Codex |
| mcp-musescoreghchen99/mcp-musescore | Skill | 140 | yesterday | MIT | A | 40 | Codex |
| jellyfin-media-playbackKnuckles-Team/jellyfin-mcp | Skill | 3 | 2d ago | MIT | A | 136 | Claude Code, Codex |
| setupAINSOF-Tech/mcp | Skill | 0 | 3d ago | MIT | A | 47 | Claude Code |
| soundtrackAINSOF-Tech/mcp | Skill | 0 | 3d ago | MIT | A | 76 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | 2d ago | Apache-2.0 | A | 187 | Claude Code |