agentmods.dev

mcp-score AGENTS.md

mcp-score AGENTS.md is an instructions file for Codex, OpenCode from tskovlund/mcp-score. It costs 1,162 tokens per session, scanned A, original, MIT.

Documentation and instructions for mcp-score, a project that generates and edits musical scores. It describes a standalone score-generation skill and an MCP server that connects to MuseScore, Dorico, or Sibelius.

In plain words
What is it for?
Use it when developing, running, or modifying mcp-score, including score generation, live score analysis, and edits such as changing keys, tempo, chords, or transposition.
Why use it?
It explains how the two parts fit together and gives developers the project structure and conventions needed to work on it.

Instructions file for CodexOpenCode

not rated 20 8d ago A scan 1,162 tokens original MIT
View the source file tskovlund/mcp-score
Install

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.

agentmods
npx agentmods add instructions/tskovlund/mcp-score/agents-md
Clone the repo
git clone --depth 1 https://github.com/tskovlund/mcp-score

Made for: Codex, OpenCode.

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.

agentmods badge for mcp-score AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tskovlund/mcp-score/agents-md.svg)](https://agentmods.dev/instructions/tskovlund/mcp-score/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tskovlund/mcp-score/agents-md"><img src="https://agentmods.dev/badge/instructions/tskovlund/mcp-score/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,162 This file is loaded in full into every session.
When invoked 1,162 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01162 $0.01162
Opus 5 $0.00581 $0.00581
Sonnet 5 $0.00232 $0.00232
Haiku 4.5 $0.00116 $0.00116

Measured 4d ago against content hash e72e88620457, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-score AGENTS.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 4d 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.

AGENTS.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-score

AI-driven music score generation and manipulation. Two complementary approaches:

  • Score generation via Claude Code skill (.claude/skills/score-generate/) — Claude writes music21 Python scripts that export MusicXML. No MCP needed; runs as a standalone skill.
  • Live score manipulation via MCP server — reads from and writes to a running score application (MuseScore, Dorico, or Sibelius) via WebSocket bridge.

Follow the code standards in CONVENTIONS.md.

Architecture

src/mcp_score/
  server.py           MCP server entry point (FastMCP)
  app.py              Shared FastMCP instance
  tools/
    connection.py     Connect/disconnect MuseScore, Dorico & Sibelius, ping, score info
    analysis.py       Read passages and measures from live score
    manipulation.py   Modify live score (barlines, chords, keys, tempo, transpose)
  bridge/
    base.py           ScoreBridge abstract base class
    remote_control.py Shared Remote Control protocol (Dorico & Sibelius)
    musescore.py      WebSocket client for MuseScore plugin
    dorico.py         Dorico defaults (thin subclass of RemoteControlBridge)
    sibelius.py       Sibelius defaults (thin subclass of RemoteControlBridge)
  musescore/
    plugin.qml        MuseScore QML plugin (WebSocket server, 19 commands)

.claude/skills/
  score-generate/     Claude Code skill for score generation via music21
    SKILL.md
    references/

tests/                pytest tests, one file per module
docs/                 Diataxis-structured documentation

Why two approaches?

Generation is best as a skill: Claude writes a complete music21 script in one shot, giving it full access to the entire music21 API. This is faster (one script vs dozens of MCP tool calls) and more flexible (no API surface to limit).

Manipulation is best as MCP: reading from and writing to a live score application requires a persistent WebSocket connection and state management that MCP handles well.

See docs/architecture.md for detailed design documentation.

Read the full file on GitHub · 118 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.

  1. 4d ago First seen · 118 lines · 1,162 tokens per session scan A e72e88620457

Subscribe to this mod's changes

mcp-score AGENTS.md is an instructions file published in the GitHub repository tskovlund/mcp-score (20 stars, last pushed 8d ago), licensed MIT. It adds 1,162 tokens to every session, about $0.0058 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.

Creative and mediaaiclaudemcpmcp-servermusescoremusic
Related

Other instructions, from other repositories

lastfm-mcp CLAUDE.md

Instructions for rianvdm/lastfm-mcp, covering claude.md, build / test / lint commands, running tests, code style and formatting (prettier).

rianvdm/lastfm-mcp · 1,582 tokens

discogs-mcp CLAUDE.md

Instructions for rianvdm/discogs-mcp, covering claude.md, project, commands, architecture and key patterns.

rianvdm/discogs-mcp · 1,193 tokens

comfyui_mcp AGENTS.md

Instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.

hybridindie/comfyui_mcp · 4,166 tokens

mixx-dj-mcp AGENTS.md

Instructions for sandraschi/mixx-dj-mcp, covering mixx-dj-mcp agent context, quick ref, key files, portmanteau tools and standards.

sandraschi/mixx-dj-mcp · 1,048 tokens

lxmusic CLAUDE.md

Instructions for tiancheng91/lxmusic, covering claude.md, 常用命令, 安装依赖, 运行测试 and 运行单个测试.

tiancheng91/lxmusic · 1,516 tokens

cascade-img AGENTS.md

Instructions for laffeyp/cascade-img, covering agents.md, what cascade-img is, and how you drive it, how to operate in this repo, the loop and tools.

laffeyp/cascade-img · 6,440 tokens