Borrowing it
Nothing to install: this file belongs to os-tack/fcp-midi. 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/os-tack/fcp-midi/main/CLAUDE.mdgit clone --depth 1 https://github.com/os-tack/fcp-midiWrote 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/instructions/os-tack/fcp-midi/claude-md)<a href="https://agentmods.dev/instructions/os-tack/fcp-midi/claude-md"><img src="https://agentmods.dev/badge/instructions/os-tack/fcp-midi/claude-md.svg" alt="Measured on agentmods" 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 | $0.00457 | $0.00457 |
| Opus 5 | $0.00229 | $0.00229 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
fcp-midi 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 7d 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.
What it actually says
fcp-midi
Project Overview
MCP server that lets LLMs compose MIDI music through semantic operation strings.
See docs/ for design documents and specifications.
Architecture
Mido-native — a mido.MidiFile is the source of truth throughout, with no
parallel semantic model between the op handlers and the file format:
- MCP Server -
src/fcp_midi/server/- Parses op strings, resolves refs, dispatches, viafcp_core.create_fcp_server()+MidiAdapter(src/fcp_midi/adapter.py) - MidiModel -
src/fcp_midi/model/midi_model.py- Wrapsmido.MidiFile; op handlers read/write mido messages directly on the tracks. ANoteIndexgives fast selector lookups (by track/pitch/channel/velocity). Undo/redo and batch atomicity are byte snapshots of the file (MidiModel.snapshot()/.restore()), not event replay.
Key Directories
src/fcp_midi/model/- MidiModel (mido-backed), NoteIndex, timing conversionssrc/fcp_midi/parser/- Operation string parser, pitch/duration/position/chord grammarsrc/fcp_midi/server/- MCP server wiring, op handlers, queries, verb registrysrc/fcp_midi/adapter.py-MidiAdapter, theFcpDomainAdapter[MidiModel, SnapshotEvent]bridging fcp-core to MidiModelsrc/fcp_midi/lib/- GM instrument/drum tables, chord library, soundfont loading
Commands
uv run pytest- Run tests (620;-m "not slow"for the fast ~604-test subset)uv run python -m fcp_midi- Start the MCP server
Conventions
- Python 3.11+
- uv for package management
- Tests co-located in
tests/ - pytest for testing
- mido for MIDI I/O (
MidiModel.save()/.load())
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.
- 7d ago First seen · 38 lines · 457 tokens per session scan A a4d711cc5a24
fcp-midi CLAUDE.md is an instructions file published in the GitHub repository os-tack/fcp-midi (7 stars, last pushed 2mo ago), licensed MIT. It adds 457 tokens to every session, about $0.0023 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.
Other instructions, from other repositories
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.
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.
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).
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).
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.
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.