agent-device
Drive iOS and Android devices for the Expensify App - testing, debugging, performance profiling, bug reproduction, and feature verification. Use when the developer needs to interact with the mobile app on a device.
Best for Mobile app developersWorks with GitHub
⌘source
- author
@Expensify- repo
- Expensify/App
- language
- TypeScript
★4.8kstars
3.7kforks
Apr 22, 2026
✦overview.md
Key Features
- ·Drive iOS and Android devices
- ·Test the Expensify mobile app
- ·Debug mobile app issues
- ·Profile mobile app performance
- ·Reproduce mobile app bugs
- ·Verify mobile app features
Use Cases
- →Testing the Expensify app on real iOS/Android devices
- →Debugging a specific mobile app issue that only occurs on device
- →Profiling mobile app performance on actual hardware
- →Reproducing a bug reported by users on their devices
- →Verifying new features work correctly on mobile platforms
Best for
- ✓Mobile app developers
- ✓QA engineers testing on devices
- ✓Performance profiling teams
Not ideal for
- !Web application testing
- !Desktop application work
- !Non-Expensify mobile apps
FAQs
name
agent-device
description
Drive iOS and Android devices for the Expensify App - testing, debugging, performance profiling, bug reproduction, and feature verification. Use when the developer needs to interact with the mobile app on a device.
allowed-tools:Bash(agent-device *) Bash(npm root *)
agent-device
Pre-flight
agent-device CLI version: !agent-device --version 2>&1 || echo "NOT_INSTALLED"
Canonical skill reference path (read these files directly for device automation guidance - bootstrap, exploration, verification, debugging): !echo "$(npm root -g)/agent-device/skills/agent-device"
If the version line above shows
NOT_INSTALLEDor a command-not-found error, STOP and instruct the developer to install it:npm install -g agent-device. All device interaction depends on it.
$install
1-click copynpx skills add Expensify/App --skill agent-deviceSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.