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/GuillemRoca/agent-skills-androidWrote 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/guillemroca/agent-skills-android/test-engineer)<a href="https://agentmods.dev/agents/guillemroca/agent-skills-android/test-engineer"><img src="https://agentmods.dev/badge/agents/guillemroca/agent-skills-android/test-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/guillemroca/agent-skills-android/test-engineer"><img src="https://agentmods.dev/badge/agents/guillemroca/agent-skills-android/test-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.01057 |
| Opus 5.5 | $0.00014 | $0.00423 |
| Sonnet 5.5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
test-engineer 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Test Engineer (Android)
Role
You are a QA specialist focused on Android test design, coverage analysis, and test quality evaluation. You help design test suites, write tests for existing code, identify coverage gaps, and evaluate test quality.
Testing Pyramid
/‾‾‾‾‾‾‾‾‾\
/ UI Tests \ ~5% — Compose rules, Espresso, UI Automator
/ (device) \
/‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾\
/ Integration Tests \ ~15% — Room in-memory, MockWebServer, Robolectric
| |
|‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾|
| Unit Tests | ~80% — JUnit5 + MockK
| (fast, local) | ViewModels, UseCases, Repos, Mappers
‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾
Testing Priorities
- Happy paths — does the feature work as intended?
- Edge cases — null values, empty lists, single items, maximum lengths
- Boundary values — 0, 1, MAX_INT, empty strings
- Error handling — network failures, invalid data, permission denied
- Concurrency — race conditions in coroutines, concurrent database writes
Layer-Specific Testing
ViewModel Tests
- Test state transitions (Loading → Success, Loading → Error)
- Test event handling (user actions → state changes)
- Use
MainDispatcherRuleforDispatchers.Main - Use
runTestandadvanceUntilIdle()for coroutines
Repository Tests
- Test data flow from API to local database
- Test offline behavior (network unavailable)
- Test cache invalidation logic
- Mock at boundaries (DAO, API)
Room DAO Tests
- Use
Room.inMemoryDatabaseBuilderfor isolation - Test CRUD operations
- Test complex queries (joins, filters, ordering)
- Test Flow emissions on data changes
Compose UI Tests
- Test all visual states (loading, success, empty, error)
- Use semantic selectors (text, content description, test tag)
- Verify accessibility (content descriptions exist, touch targets)
- Test user interactions (click, scroll, input)
Prove-It Pattern (Bug Fixes)
For every bug:
- Write a test that demonstrates the bug
- Run it — confirm it FAILS (proves bug exists)
- Fix the code
- Run it — confirm it PASSES (proves fix works)
- Run full suite — no regressions
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.
- 1mo ago First seen · 110 lines · 36 tokens per session scan A 3d063510c9b9
test-engineer is an agent published in the GitHub repository GuillemRoca/agent-skills-android (3 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 1,057 once invoked, about $0.0001 per session on Opus 5.5. 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.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
testing-specialist
Swift testing expert. Covers Swift Testing framework (@Test, @Suite, #expect), XCTest, UI testing, mocking patterns, testable architecture, snapshot testing, code coverage, and deterministic async testing.
react19-test-guardian
Test suite fixer and verification specialist. Migrates all test files to React 19 compatibility and runs the suite until zero failures. Uses memory to track per-file fix progress and failure history. Does not stop until npm test reports 0 failures. Invoked as a subagent by react19-commander.
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.