agentmods.dev

mx impl.instructions.md

Project-specific implementation rules for webern/mx, a C++ library that connects programs to MusicXML, a standard format for written music. The rules cover conversion between the library's internal and public data structures.

In plain words
What is it for?
Use them when changing readers, writers, converters, sentinel values, or timing logic in the mx::impl part of the project.
Why use it?
They help prevent lost data, broken read/write round trips, invalid MusicXML, and incorrect timing information.

Instructions file for GitHub Copilot

93 3d ago A scan 290 tokens original MIT
View the source file webern/mx
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/webern/mx/impl
Clone the repo
git clone --depth 1 https://github.com/webern/mx

Made for: GitHub Copilot.

Per session 290 This file is loaded in full into every session.
When invoked 290 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 $0.00290 $0.00290
Opus 5 $0.00145 $0.00145
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured 2d ago against content hash b9af688de6c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mx impl.instructions.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.

.github/instructions/impl.instructions.md · 20 lines

What it actually says

mx::impl translates between mx::core (generated MusicXML model) and mx::api (public structs). Review for:

  • Read/write symmetry: a feature read in a *Reader must also be written by the matching *Writer, and vice versa. A one-sided change silently drops data on round-trip -- flag it.
  • Silent data loss: an empty case/break, a value read but never stored, or a field never consulted on write is only acceptable with a comment saying the drop is intentional.
  • Sentinel contracts must hold on both sides (e.g. time-modification 1/1 means "absent"; -1 means "unspecified"). A writer emitting a sentinel or a reader failing to produce one breaks round-trip.
  • MX_DEBUG_THROW is a no-op in release builds; it must not be the only guard on a path that would otherwise write invalid or truncated MusicXML.
  • Tick time: positions are absolute (tickTimePosition against ScoreData::ticksPerQuarter); writers must synthesize <backup>/<forward>/<divisions>, never expect callers to.
  • No new anonymous namespaces (unity-build rule; use named helpers / k-prefixed constants).
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. 2d ago First seen · 20 lines · 290 tokens per session scan A b9af688de6c2

Subscribe to this mod's changes

mx impl.instructions.md is an instructions file published in the GitHub repository webern/mx (93 stars, last pushed 3d ago), licensed MIT. It adds 290 tokens to every session, about $0.0014 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 mediac-plus-plusmusicmusic-notationmusicxmlxmlxml-dom
Related

Other instructions, from other repositories

librosa AGENTS.md

Instructions for librosa/librosa, covering agent interaction policy for librosa, 1. automated platform interactions, 2. exception for project-authorized automation and 3. machine-readable directive.

librosa/librosa · 212 tokens

spotatui copilot-instructions.md

Instructions for LargeModGames/spotatui, covering copilot instructions for spotatui, build & run, ci checks (run before opening a pr), run a single test and example.

LargeModGames/spotatui · 7,494 tokens

musicbox AGENTS.md

Instructions for darknessomi/musicbox, covering agents.md, cursor cloud specific instructions, running the app, audio backends (system deps, not in update script) and network / api note.

darknessomi/musicbox · 579 tokens

nuclear AGENTS.md

AGENTS.md instructions for nukeop/nuclear, covering agents.md, project overview, packages, commands and development.

nukeop/nuclear · 3,328 tokens

nuclear copilot-instructions.md

Copilot instructions for nukeop/nuclear, covering nuclear music player - copilot instructions, project overview, key features, tech stack and packages.

nukeop/nuclear · 1,235 tokens

pytheory CLAUDE.md

Instructions for kennethreitz/pytheory, covering claude code instructions, release process, version bumping, testing and publishing.

kennethreitz/pytheory · 348 tokens