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/yefee8/mufify/agents-mdgit clone --depth 1 https://github.com/Yefee8/mufifyWhat 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 | $0.03747 | $0.03747 |
| Opus 5 | $0.01873 | $0.01873 |
| Sonnet 5 | $0.00749 | $0.00749 |
| Haiku 4.5 | $0.00375 | $0.00375 |
Grade A, and why
mufify 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working in this repository. Human contributors should read this too — it's the house style.
Note:
create-expo-appgenerates its ownAGENTS.mdandCLAUDE.md. Merge this file into the generated one rather than keeping two competing sets of rules.
Project
An offline-only local music player for Android, built with React Native and Expo. Plays FLAC and other lossless formats from the device. Local playlists, multiple shuffle algorithms, on-device listening statistics, dark/light themes, Turkish and English.
No network. No accounts. No telemetry. No analytics SDK. If a change introduces a network call, it is wrong. This is the app's core promise and the reason it exists.
Setup
Requirements: Node 22+, JDK 17 or 21, Android Studio with SDK Platform 36+, macOS or Linux.
(Expo SDK 57 compiles against 36; this said 35 until app.sh checked it and was wrong.)
Environment (macOS)
None of this is set by default. Put it in ~/.zshrc — every "it works on my machine" failure in
this project so far has been one of these three lines missing.
# Android Studio's bundled JBR is a perfectly good JDK. No separate install needed.
export JAVA_HOME="/Applications/Android Studio.app/Contents/jbr/Contents/Home"
export ANDROID_HOME="$HOME/Library/Android/sdk"
export PATH="$JAVA_HOME/bin:$ANDROID_HOME/platform-tools:$ANDROID_HOME/emulator:$PATH"
Verify before blaming the code:
java -version # 17 or 21
adb devices # your device, "device" not "unauthorized" or "offline"
npx expo-doctor
Daily loop
npm install
npx expo start --dev-client # this is the normal one — JS/TS changes hot reload
npm run lint
npm run typecheck
npm test
npm run db:generate # drizzle-kit: generate migration after schema change
npx expo run:android is only for native changes: adding or removing a native dependency,
editing app.json, or changing a config plugin. It is a ten-minute build. Reaching for it after a
TypeScript edit is the most common way to waste an afternoon here.
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 · 316 lines · 3,747 tokens per session scan A e2b024f7819e
mufify AGENTS.md is an instructions file published in the GitHub repository Yefee8/mufify (11 stars, last pushed 13d ago), licensed MIT. It adds 3,747 tokens to every session, about $0.0187 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.
Other instructions, from other repositories
tolgee-platform AGENTS.md
AGENTS.md instructions for tolgee/tolgee-platform, covering agents.md, repository structure, backend development, database migrations and backend testing.
i1n-cli copilot-instructions.md
Instructions for Pakvothe/i1n-cli, covering i1n — localization as code, project setup, translation file structure, tone & voice and cli commands.
i18n-tools-mcp CLAUDE.md
Claude Code instructions for Trivle/i18n-tools-mcp, covering claude.md, project overview, commands, architecture and conventions.
openscreen AGENTS.md
Instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
intlayer CLAUDE.md
Instructions for aymericzip/intlayer, covering repo layout, commands (run from root), content declaration flow, git and commit conventions.
claude-code-zh-cn AGENTS.md
Instructions for taekchef/claude-code-zh-cn, covering claude-code-zh-cn, 项目结构, 数据流, 技术要点 and 维护流程规则.