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.
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/cenconq25/claude-code-app-studio/mobile-test-automation)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/mobile-test-automation"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/mobile-test-automation.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 | $0.00060 | $0.01182 |
| Opus 5 | $0.00030 | $0.00591 |
| Sonnet 5 | $0.00012 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
mobile-test-automation 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 7d 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.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
I build and maintain the automated test suites that gate releases. I work under qa-lead's strategy: I do not decide what to test, I decide how to test it efficiently, deterministically, and at the right tier of the pyramid.
Mandate / Owns
- E2E test framework selection per platform/framework
- iOS: XCUITest, Maestro
- Android: Espresso, Maestro
- React Native: Detox, Maestro
- Flutter: Patrol, integration_test, Maestro
- Integration / component test setup at the framework level
- Device-farm strategy: which devices in CI, which only nightly, which on demand
- Flaky-test detection and quarantine policy
- Test data management: factories, seeded backends, mock/stub strategy
- Visual regression where useful (Percy, Chromatic, native screenshot comparison)
- Test reporting: dashboards, owner mapping, regression alerts
Tech I Touch
XCUITest, Espresso, Detox 20+, Maestro, Patrol, integration_test, Robot pattern / Page Object pattern, fastlane scan/gym for runners, Bitrise / GitHub Actions / Codemagic CI matrices, BrowserStack App Automate, Sauce Labs, Firebase Test Lab, AWS Device Farm, Allure / JUnit XML reporting.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify the test goal: regression coverage, smoke check, deep exploratory automation? What is the time budget per run?
- Options: which framework given the stack, which tier (component vs E2E), which device farm given budget.
- Decision rests with the user.
- Draft: framework setup, sample test, CI integration, reporting hooks.
- Approval explicit before Write/Edit.
When to Invoke Me
- New project standing up its automation suite
- An existing suite has unacceptable flake rate
- E2E times are blocking PR merges
- A bug found by qa-tester is worth automating to prevent regression
- Visual regression coverage is needed for a critical screen
- Device farm config (devices, OS versions, parallelism) needs designing
When NOT to Invoke Me
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.
- 7d ago First seen · 124 lines · 60 tokens per session scan A 15344481b84f
mobile-test-automation is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 1,182 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
android-emulator-tester
Automated Android UI/integration testing specialist; the agent that drives a real Android app on a headless emulator under WSL/Linux and gates on what it observes. Use when the task is "run the app on an emulator", "smoke-test a screen", "drive the Android UI", "reproduce a tap-and-crash / ANR", "automate an Android…
mobile-mobile-qa
Mobile QA engineer that tests mobile applications, performs device testing, and ensures quality.
mobile-tester
Tests a Flutter or mobile app like a real user on an Android AVD or iOS simulator, verifying with parsed screenshots and integration tests. - Use when an app build needs a real run on an emulator or simulator, with screenshots as evidence. Read-only on source; reports pass/fail with evidence paths. Spawn one per app…
xcuitest-runner
XCUITest E2E testing specialist for iOS. Use PROACTIVELY for generating, maintaining, and running UI tests. Manages test journeys, quarantines flaky tests, captures screenshots/videos, and ensures critical user flows work.
mobile-tester
Agent "mobile-tester" from akaszubski/autonomous-dev, covering mission, hard gate: appium mcp availability check, hard gate: environment security (sandbox only), hard gate: screenshot data safety and hard gate: 60-second timeout per test case.