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 agentmods add instructions/matheusfillipe/midifier/agents-mdgit clone --depth 1 https://github.com/matheusfillipe/midifierWhat 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 | $0.01071 | $0.01071 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
midifier 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for agents working in this repo. CLAUDE.md is a symlink to this file, so there is
one set of instructions rather than two that drift.
What this is
An API that turns a recording into a multi-track General MIDI file: it identifies which instruments are playing, transcribes each, and names and assigns the tracks. It feeds kinesthesia, which renders MIDI as falling notes to practise against.
Toolchain
uv for everything. Never call pip or a bare python.
uv sync --extra dev # install
uv run pytest # tests
uv run mypy src tests # types, strict
uv run ruff check --fix . # lint
uv run ruff format . # format
uv run pre-commit run -a # everything CI runs
uv run python -m midifier # serve the API
uvx for one-off tools that are not dependencies.
Non-negotiables
- mypy strict. No
Any, no untyped defs, no# type: ignorewithout a reason on the same line. If typing something is hard, that usually means the design is unclear. - One import per line.
force-single-line = true; do not group with commas or parentheses. - Coverage stays at or above 80%. Add tests with the code, not afterwards.
- Every check runs in pre-commit, and CI runs pre-commit. Adding a check anywhere else splits the definition of "clean" in two.
- No bare
except Exception. Catch what can actually be raised.
Style
Comments are rare and earn their place. The code says what it does; a comment exists only for a non-obvious why, a constraint, or a trap that would invite a wrong "simplification". Never narrate a change ("was X, now Y") — write code as though it always looked this way.
Prefer deleting to adding. The pipeline reached its current quality mostly by removing stages that sounded clever and measured worse; treat new stages with the same suspicion.
Where things are
src/midifier/
config.py settings, all from the environment, prefix MIDIFIER_
api.py REST surface, async job pattern
mcp.py MCP tools over the same job store
storage.py local filesystem or S3/MinIO behind one protocol
fetch.py SSRF-guarded URL fetching
jobs.py job model and in-memory store
midi/
cleanup.py repairs the decoder's characteristic defects
segments.py decodes long audio in overlapping pieces and stitches them
consolidate.py folds lanes that are one part under two names
tests/ mirrors src; e2e/ needs the model and is opt-in
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.
- 2d ago First seen · 102 lines · 1,071 tokens per session scan A d3e969da98f9
midifier AGENTS.md is an instructions file published in the GitHub repository matheusfillipe/midifier (1 stars, last pushed 27d ago), licensed MIT. It adds 1,071 tokens to every session, about $0.0054 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
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.