morningstar-midi-mcp: Instructions file for Claude Code

CLAUDE.md

morningstar-midi-mcp CLAUDE.md is an instructions file for Claude Code from Turik1/morningstar-midi-mcp. It costs 531 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for developing an MCP server that configures Morningstar Engineering MIDI controllers. MIDI is a protocol used to send control messages between musical devices and software.

In plain words
What is it for?
Use it to work on MIDI message encoding, USB connections, device models, presets, configuration and MCP tool registration.
Why use it?
It explains the project structure, build and test commands, Git rules and communication constraints, reducing errors when changing the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Turik1/morningstar-midi-mcp's own configuration. It tells Claude Code how to work on morningstar-midi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything morningstar-midi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Turik1/morningstar-midi-mcp. 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/Turik1/morningstar-midi-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Turik1/morningstar-midi-mcp

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.

agentmods badge for morningstar-midi-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/turik1/morningstar-midi-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/turik1/morningstar-midi-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/turik1/morningstar-midi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/turik1/morningstar-midi-mcp/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.

agentmods 80×15 button for morningstar-midi-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/turik1/morningstar-midi-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/turik1/morningstar-midi-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 531 This file is loaded in full into every session.
When invoked 531 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00531 $0.00531
Opus 5 $0.00266 $0.00266
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 12d ago against content hash 84d5cfcbc31f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

morningstar-midi-mcp 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 12d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

morningstar-midi-mcp

MCP server for configuring Morningstar Engineering MIDI controllers via natural language.

Stack

  • TypeScript ES modules ("type": "module"), Node16 module resolution, strict mode
  • npm test — vitest run; npm run build — tsc to build/
  • zod v4 (not v3) — API identical for basic schemas; MCP SDK supports both
  • Imports use .js extension for .ts source files (Node16 ESM requirement)

Project Structure

  • src/protocol.ts — SysEx message encoding/decoding, checksum
  • src/commands.ts — High-level Morningstar controller commands
  • src/midi.ts — USB-MIDI connection layer (jzz wrapper)
  • src/models.ts — Controller model definitions and physical layouts
  • src/devices.ts — OpenMIDI device database loader and search
  • src/tools.ts — MCP tool registrations
  • src/config.ts — setup.yaml loading
  • src/state.ts — Shadow state for tracking written preset messages
  • src/index.ts — Entry point
  • docs/superpowers/specs/ — Design spec
  • docs/superpowers/plans/ — Implementation plan

Git

  • Conventional commits required: feat:, fix:, docs:, refactor:, etc.

MCP Constraints

  • stdio transport — NEVER console.log(), only console.error() (corrupts JSON-RPC)
  • Tool registration: server.tool(name, { param: z.string() }, handler)

OpenMIDI Submodule (openmidi/)

  • CC number field is value (NOT number) in YAML files
  • Brand/device names from mapping.json, not directory names
  • Path: openmidi/data/brands/<brand-slug>/<model-slug>.yaml

Key Module Facts

  • resolvePreset(identifier, modelName) — second arg is model name string, not device ID
  • DeviceDatabase.search() — case-insensitive substring on brand + device
  • ShadowState tracks written messages locally (SysEx can't read preset messages back)
  • buildSysExMessage() — use in tests to construct valid mock SysEx responses

jzz Type Declarations (src/jzz.d.ts)

  • Do NOT use extends Promise<Self> pattern — causes TS1062 circular reference
  • Use Promise<T> return types on methods instead

Read the full file on GitHub · 45 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. 12d ago First seen · 45 lines · 531 tokens per session scan A 84d5cfcbc31f

Subscribe to this mod's changes

morningstar-midi-mcp CLAUDE.md is an instructions file published in the GitHub repository Turik1/morningstar-midi-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 531 tokens to every session, about $0.0027 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 2026-08-31.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens