androir-mcp: Instructions file for Claude Code

CLAUDE.md

androir-mcp CLAUDE.md is an instructions file for Claude Code from benasbarciauskas/androir-mcp. It costs 271 tokens per session, scanned A, original, Apache-2.0.

A set of Claude Code instructions for an MCP server that controls the owner's Android devices through ADB and UI automation. ADB is Android's command-line connection for reading screens, sending input, and launching apps.

In plain words
What is it for?
Use it when building or maintaining personal Android automation for screen reading, taps, swipes, typing, app launching, and replayable actions.
Why use it?
It defines the allowed scope and safe coding rules for device automation, including input validation, timeouts, and secret handling.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is benasbarciauskas/androir-mcp's own configuration. It tells Claude Code how to work on androir-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything androir-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to benasbarciauskas/androir-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.

Copy the file
curl -O https://raw.githubusercontent.com/benasbarciauskas/androir-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/benasbarciauskas/androir-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for androir-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/benasbarciauskas/androir-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/benasbarciauskas/androir-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/benasbarciauskas/androir-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/benasbarciauskas/androir-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.

agentmods 80×15 button for androir-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/benasbarciauskas/androir-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/benasbarciauskas/androir-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 271 This file is loaded in full into every session.
When invoked 271 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00271 $0.00271
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 10d ago against content hash abb96a5a2c09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

androir-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 10d 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.

- Shell adb via child_process with an argv array — NEVER a shell string.
CLAUDE.md · 26 lines

What it actually says

androir-mcp

An adb/uiautomator-backed MCP server for automating real Android devices: screen reading, input (tap/swipe/type), and app launching from any MCP client.

Scope guardrail (enforced)

Single owner, the owner's own Android devices. Build screen reading + input + launching + replayable personal automation. Do NOT build anti-detection / evasion / "humanization-for-avoidance", proxy/SIM rotation, or multi-account farm orchestration aimed at evading platform integrity systems. If a request drifts there, stop and surface it.

Conventions

  • Node + TypeScript, @modelcontextprotocol/sdk, stdio transport.
  • Shell adb via child_process with an argv array — NEVER a shell string.
  • Validate every serial (charset [A-Za-z0-9.:_-], len <= 128) and escape every interpolated value before it reaches adb.
  • Keep files focused; one tool group per module.
  • Per-call timeout with process-group kill.

Security

  • Public repo: NEVER commit secrets, .env, tokens, keys. A pre-push secret scan blocks this; do not bypass it.
  • No secrets or PII in logs or tool output. Concise errors, no stack traces to the model.
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. 10d ago First seen · 26 lines · 271 tokens per session scan A abb96a5a2c09

Subscribe to this mod's changes

androir-mcp CLAUDE.md is an instructions file published in the GitHub repository benasbarciauskas/androir-mcp (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 271 tokens to every session, about $0.0014 per session on Opus 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens