Agent-Android CLAUDE.md

A set of project instructions for DroidBridge, an Android tool, covering its working context, commands, architecture, and documentation rules.

In plain words
What is it for?
Use it when editing, checking, testing, packaging, or documenting DroidBridge and its Android, device, runner, and server components.
Why use it?
It gives the agent the project-specific information needed to work safely and avoid outdated assumptions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/xiaoran7/agent-android/claude-md
Clone the repo
git clone --depth 1 https://github.com/xiaoran7/Agent-Android
Per session 296 This file is loaded in full into every session.
When invoked 296 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00296 $0.00296
Opus 5 $0.00148 $0.00148
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00030 $0.00030

Measured yesterday against content hash a00b48d6ad3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Agent-Android 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 yesterday.

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.

CLAUDE.md · 30 lines

What it actually says

DroidBridge working context

Commands

.\scripts\setup_venv.ps1
.\.venv\Scripts\python.exe -m ruff check .
.\.venv\Scripts\python.exe -m ruff format --check .
.\.venv\Scripts\python.exe -m pytest -q
.\.venv\Scripts\python.exe -m build

Python must be 3.11. Do not run packaging scripts until their remaining 0.6.x/Web assumptions have been reconciled with the 2.0 CLI.

Architecture

  • mcp_server/server.py: MCP registration and stdio/SSE entrypoint.
  • controller/: shared tools, OCR, scrcpy, events, and command queue.
  • devices/: ADB connection, discovery, and pairing.
  • runner/: outbound Android Runner protocol and sessions.
  • apps/runner-android/: Android Runner APK.

The ADB and Runner drivers do not have identical capabilities. Verify the target driver before documenting or testing a tool.

Documentation

README is the user entrypoint, docs/ARCHITECTURE.md owns internal design, docs/gotchas.md contains only active reusable pitfalls, and CHANGELOG.md records history. Do not restore the removed browser-console or tray narrative unless the implementation returns.

Preserve legal files and the duplicate third-party resources required by packaging.

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. yesterday First seen · 30 lines · 296 tokens per session scan A a00b48d6ad3b

Subscribe to this mod's changes

Agent-Android CLAUDE.md is an instructions file published in the GitHub repository xiaoran7/Agent-Android (1 stars, last pushed 3d ago), licensed MIT. It adds 296 tokens to every session, about $0.0015 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.

Related

Other instructions, from other repositories

scrcpy-mcp AGENTS.md

Instructions for JuanCF/scrcpy-mcp, covering agents.md, project overview, project documentation, build/lint/test commands and build the project.

JuanCF/scrcpy-mcp · 1,693 tokens

android-agent CLAUDE.md

Instructions for ghost-in-the-droid/android-agent, covering ghost in the droid — agent tool rules, mcp tool: opencamera, mcp tool: speaktext and general rule.

ghost-in-the-droid/android-agent · 324 tokens

native-devtools-mcp AGENTS.md

AGENTS.md instructions for vectora-foundry/native-devtools-mcp, covering agent context: native-devtools-mcp, 🧠 core reasoning loop, 🗺️ capabilities matrix (strategy guide), 🛠️ tool definitions & schemas and 1. vision & perception (the "eyes").

vectora-foundry/native-devtools-mcp · 8,302 tokens

uiautomator2-mcp-server AGENTS.md

Instructions for tanbro/uiautomator2-mcp-server, covering uiautomator2-mcp-server, project overview, project structure, development setup and install dependencies (uses uv lock file).

tanbro/uiautomator2-mcp-server · 3,906 tokens

stremio-mcp AGENTS.md

Instructions for netixc/stremio-mcp, covering project instructions, authoritative commands, change-to-check mapping, project-specific constraints and authoritative references.

netixc/stremio-mcp · 1,406 tokens

uiautomator2-mcp-server CLAUDE.md

Instructions for tanbro/uiautomator2-mcp-server, a project described as: A MCP (Model Context Protocol) server that provides tools for controlling and interacting with Android devices using uiautomator2.

tanbro/uiautomator2-mcp-server · 10 tokens