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.
curl -O https://raw.githubusercontent.com/benasbarciauskas/androir-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/benasbarciauskas/androir-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/benasbarciauskas/androir-mcp/claude-md)<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.
<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>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 | $0.00271 | $0.00271 |
| Opus 5 | $0.00135 | $0.00135 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
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. 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.
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.
- 10d ago First seen · 26 lines · 271 tokens per session scan A abb96a5a2c09
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.
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.
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.
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).
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.
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).
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.