Borrowing it
Nothing to install: this file belongs to desamtralized/adb-mcp. 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/desamtralized/adb-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/desamtralized/adb-mcpWrote 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/desamtralized/adb-mcp/claude-md)<a href="https://agentmods.dev/instructions/desamtralized/adb-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/desamtralized/adb-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/desamtralized/adb-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/desamtralized/adb-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00420 | $0.00420 |
| Opus 5.5 | $0.00168 | $0.00168 |
| Sonnet 5.5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
adb-mcp CLAUDE.md scanned grade A with 1 finding 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 2mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Each tool maps to specific ADB commands via `child_process.exec` What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) server that provides ADB tools for Android device management, specifically focused on WiFi connections and screenshot capture. The server exposes 5 main tools through the MCP protocol for remote Android device interaction.
Architecture
Core Components:
- MCP Server: Single-file TypeScript implementation (
src/index.ts) using@modelcontextprotocol/sdk - Tool Handlers: Five ADB command wrappers exposed as MCP tools
- Transport: Uses stdio transport for MCP communication
Key Design Patterns:
- Each tool maps to specific ADB commands via
child_process.exec - Async/await pattern with promisified exec for command execution
- Centralized error handling with MCP-specific error codes
- Tool schema validation using JSON Schema
Development Commands
# Build the project
npm run build
# Development with watch mode
npm run dev
# Start the MCP server
npm start
# Install dependencies
npm install
Tool Architecture
The MCP server exposes these tools:
adb_connect_wifi- Connect to Android device over WiFiadb_screenshot- Capture device screenshotsadb_list_devices- List connected devicesadb_disconnect- Disconnect from WiFi deviceadb_device_info- Get device information
All tools execute ADB commands via execAsync and return results through MCP's content format.
Prerequisites
- ADB must be installed and available in PATH
- Android device with USB debugging enabled
- For WiFi connections: device must be on same network and have
adb tcpip 5555run first
Error Handling
The server uses MCP's error system with McpError and appropriate error codes. ADB command failures are caught and wrapped in MCP errors with descriptive messages.
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.
- 2mo ago First seen · 57 lines · 420 tokens per session scan A 88999565eaed
adb-mcp CLAUDE.md is an instructions file published in the GitHub repository desamtralized/adb-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 420 tokens to every session, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
adb-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adb-mcp CLAUDE.mddesamtralized/adb-mcp | Instructions file | 0 | 1y ago | MIT | A | 420 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | today | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |