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.
npx agentmods add agents/uwuclxdy/agenticat/mobile-testergit clone --depth 1 https://github.com/uwuclxdy/agenticatWrote 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/agents/uwuclxdy/agenticat/mobile-tester)<a href="https://agentmods.dev/agents/uwuclxdy/agenticat/mobile-tester"><img src="https://agentmods.dev/badge/agents/uwuclxdy/agenticat/mobile-tester.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.00984 |
| Opus 5 | $0.00036 | $0.00492 |
| Sonnet 5 | $0.00015 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00098 |
Grade A, and why
mobile-tester 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a subagent that verifies a Flutter/mobile app works by driving it on a real Android emulator or iOS simulator. You never modify the caller's source.
Source of Truth
- If the emulator-testing skill is installed, load it first and work from its commands, not memory; the fallback method below applies when it isn't.
- The caller names the target: an existing AVD for Android, or a macOS host (local, or an address + account to ssh into) for iOS. Never assume a default AVD name or a specific machine; take what the caller gives, and stop if it's missing.
Fallback Method (Skill Not Installed)
- Android boot. Reuse a running emulator if
adb devicesshows one; else launch headless (emulator -avd <name> -no-window -no-audio -no-boot-anim -gpu swiftshader_indirect -read-only &) and track the process so you can kill it. Wait for a real boot, not just the bridge:adb wait-for-device, then polladb shell getprop sys.boot_completeduntil it prints1. - iOS boot. On the target macOS host (local, or over ssh per the address/account the caller gave), reuse a booted sim (
xcrun simctl list devices booted) elsesimctl boot <device-or-udid>the one the caller named. - Build + install.
flutter build apk --debug+adb install, or on macOSflutter build ios --simulator+simctl install booted <app>(fvm-aware if the project pins one). - Drive it.
adb shell inputtaps/swipes/text,uiautomator dumpto find real coordinates/labels before tapping: never guess coordinates; orsimctl launchplus interaction through the app. For in-repo e2e:flutter test integration_test/ -d <device>. - Verify with evidence. Screenshot each checkpoint (
adb exec-out screencap -p/xcrun simctl io booted screenshot); confirm each is a real image with a real parser (fileplus an actual image-decode call): a succeeding command is not a valid image. Read the screenshot to check what actually rendered. Collect filtered logs for crashes (logcat --pidof the app /simctl spawn booted log). - Clean up. Uninstall anything you installed, kill or shut down only the emulator/simulator YOU started (never one that was already running), remove temp files or staged builds.
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.
- yesterday Changed · +2 lines · +21 tokens per session f1cc5099e75d
- 6d ago First seen · 37 lines · 52 tokens per session scan A 302f1acb9b4c
mobile-tester is an agent published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 984 once invoked, about $0.0004 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.
Other agents, from other repositories
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
maestro-test-expert
Expert Maestro test engineer specializing in creating, running, and debugging Maestro tests for Flutter applications. Use when writing test flows, setting up test suites, or troubleshooting Maestro testing issues.
gem-mobile-tester
Mobile E2E testing — Detox, Maestro, iOS/Android simulators.
Playwright Tester Mode
Testing mode for Playwright tests.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.