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/us-all/android-mcp-server/claude-mdgit clone --depth 1 https://github.com/us-all/android-mcp-serverWrote 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/us-all/android-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/us-all/android-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/us-all/android-mcp-server/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 | $0.03597 | $0.03597 |
| Opus 5 | $0.01799 | $0.01799 |
| Sonnet 5 | $0.00719 | $0.00719 |
| Haiku 4.5 | $0.00360 | $0.00360 |
Grade A, and why
android-mcp-server 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 3d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
이 파일은 Claude Code가 이 저장소에서 작업할 때 참고하는 컨텍스트입니다.
프로젝트 개요
@us-all/android-mcp — ADB 기반 Android 디바이스 관리 MCP 서버. 75 도구로 디바이스/앱/UI/logcat/에뮬레이터/파일/시스템/디버그 영역 커버. Pure ADB (Appium / uiautomator2 의존성 없음).
- 타겟: Android 디바이스 또는 에뮬레이터 (
adb필요) - 런타임: Node 20+, stdio transport, TypeScript strict
- 포지셔닝: Android-only specialist. 크로스플랫폼은 mobile-next/mobile-mcp
- 표준: @us-all MCP Standard 준수
디렉토리
src/
├── index.ts # MCP 서버 + tool() 헬퍼 + 카테고리별 등록
├── config.ts # ENV 로딩 (ANDROID_TOOLS / ANDROID_DISABLE 토글)
├── adb.ts # execFile 기반 ADB wrapper
├── tool-registry.ts # CATEGORIES + @us-all/mcp-toolkit
├── resources.ts # MCP Resources (android:// URI)
└── tools/
├── utils.ts # wrapToolHandler, shellEscape, validation helpers
├── extract-fields.ts # toolkit re-export
├── device.ts apps.ts ui.ts logcat.ts emulator.ts
├── files.ts system.ts debug.ts shell.ts
└── aggregations.ts # analyze-app
fixtures/test-app/ # Android Gradle 테스트 앱 (스모크용)
Build & Run
pnpm install
pnpm build # tsc → dist/
pnpm test # vitest unit tests
pnpm smoke # 실 디바이스 대상 스모크 (ADB 필요)
pnpm token-stats # tools/list 토큰 측정
카테고리 (10)
ANDROID_TOOLS=device,ui,apps,logcat 같이 ENV로 일부만 로드.
| 카테고리 | 포함 도구 |
|---|---|
device |
list-devices, get-device-info |
apps |
install, uninstall, list, clear, permissions, analyze-app |
ui |
tap, swipe, screenshot, dump-hierarchy, find, scroll, annotated-screenshot |
logcat |
logcat capture, filter, crash extraction |
emulator |
AVD start/stop/snapshot |
files |
push, pull, exists, ls |
system |
settings, network, battery, display, locale, broadcast |
debug |
dumpsys, getprop, processes, doctor, mem/gfx/cpu info |
shell |
raw shell exec (별도 ANDROID_MCP_ALLOW_SHELL 게이트) |
meta |
search-tools (항상 활성) |
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.
- 3d ago First seen · 128 lines · 3,597 tokens per session scan A 3d3c6b18b04d
android-mcp-server CLAUDE.md is an instructions file published in the GitHub repository us-all/android-mcp-server (10 stars, last pushed 1mo ago), licensed MIT. It adds 3,597 tokens to every session, about $0.0180 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
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
MobiAI-Core CLAUDE.md
Instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.
freetube CLAUDE.md
Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.
ConsultMe CLAUDE.md
Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
phone-mcp CLAUDE.md
Instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
android-media-pack CLAUDE.md
Instructions for sunnat629/android-media-pack, covering claude.md, what this repository is, commands, markdown lint (config in .markdownlint-cli2.jsonc) and shell script lint.