A guide and command-line tool for controlling Android phones and emulators through ADB, the standard Android debugging connection. It supports actions such as tapping, swiping, typing, launching apps, and taking screenshots.

Use it to inspect an Android screen, tap controls, enter text, press keys, open apps, take screenshots, and automate device interactions.

It lets a coding agent interact with an Android device instead of requiring each action to be performed by hand. The device must be connected with USB debugging enabled, or an emulator must be running.

android-use — Skill by iurysza

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 skills/iurysza/android-use/android-use

Any agent

npx skills add iurysza/android-use --skill android-use

Clone the repo

git clone --depth 1 https://github.com/iurysza/android-use

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,911 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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.

Model	Per session	Once invoked
Fable 5	$0.00033	$0.02911
Opus 5	$0.00016	$0.01456
Sonnet 5	$0.00007	$0.00582
Haiku 4.5	$0.00003	$0.00291

Measured 2d ago against content hash f67ef37d3311, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

android-use scanned grade C with 2 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 2d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/iurysza/android-use/main/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/iurysza/android-use/main/install.sh | bash

SKILL.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Device Control

CLI for Android device control via ADB. Requires device connected with USB debugging enabled.

Prerequisites

Before using this skill:

Android device with USB debugging enabled
ADB installed (adb version should work)
Device connected via USB or emulator running

Agent Installation (Autonomous Setup)

When this skill is not installed, agents should:

Run installer (recommended):

curl -fsSL https://raw.githubusercontent.com/iurysza/android-use/main/install.sh | bash

Installed structure:
- ~/.config/opencode/skill/android-use/SKILL.md
- ~/.config/opencode/skill/android-use/scripts/android-use
- ~/.config/opencode/skill/android-use/references/
- ~/.config/opencode/skill/android-use/assets/
- ~/.config/opencode/skill/android-use/repo/

Verify installation:

~/.config/opencode/skill/android-use/scripts/android-use check-device

Quick Start

android-use check-device        # List connected devices
android-use get-screen          # Get UI hierarchy (compact JSON)
android-use tap 540 960         # Tap at coordinates
android-use type-text "Hello"   # Type text
android-use key HOME            # Press key
android-use screenshot ./screen.png  # Capture screen

Core Agent Workflow

STEP 1: Check device

android-use check-device

Lists all connected devices
Note the serial number if multiple devices
For "phone" use [PHYSICAL] device
For "emulator" use [EMULATOR] device

STEP 2: Get screen state

android-use get-screen

Returns compact JSON with pre-calculated tap coordinates
Search for: text, contentDesc, resourceId
Use the center field for coordinates (e.g., "center": [540, 289])
Cache location: /tmp/.ai-artifacts/skills/android-use/screen.json

STEP 3: Execute action

Tap: android-use tap <center_x> <center_y>
Type: android-use tap <field_x> <field_y> then android-use type-text "text"
Swipe: android-use swipe <x1> <y1> <x2> <y2> [duration_ms]
Key: android-use key <KEY_NAME> (HOME, BACK, ENTER, etc.)

Read the full file on GitHub · 362 lines

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.

2d ago First seen · 362 lines · 33 tokens per session scan C f67ef37d3311

Subscribe to this mod's changes

android-use is a skill published in the GitHub repository iurysza/android-use (18 stars, last pushed 6mo ago), licensed MIT. It adds 33 tokens to every session and 2,911 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM Mobile adb agentic-ai agents android automation device-control skill

agent-device

Automates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands.

callstack/agent-device · 69 tokens

android-emulator

Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device.

callstack/agent-device · 65 tokens

ios-simulator

Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.

callstack/agent-device · 69 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens

solopi-ai

通过 SoloPi 的机器可读 CLI 编译和执行 AI 验证计划，管理签名端侧 ExecuTorch 决策模型、持久设备池、无人值守任务、安卓设备、应用、动作、配置、用例步骤与交互录制、回放及性能历史、动态 Agent、批量与重复执行、性能监控、压力测试和证据。适用于需求/AC 到 Result Judge 三态结论、cloud/on-device 决策切换、模型发布门禁，以及 generation 租约的多设备 CI 执行。.

alipay/SoloPi · 127 tokens

android-use