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 skills add krutikJain/android-agent-skills --skill android-testing-uigit clone --depth 1 https://github.com/krutikJain/android-agent-skillsWrote 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/skills/krutikjain/android-agent-skills/android-testing-ui)<a href="https://agentmods.dev/skills/krutikjain/android-agent-skills/android-testing-ui"><img src="https://agentmods.dev/badge/skills/krutikjain/android-agent-skills/android-testing-ui.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 | $0.00024 | $0.01053 |
| Opus 5 | $0.00012 | $0.00526 |
| Sonnet 5 | $0.00005 | $0.00211 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
android-testing-ui 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 3d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android Testing UI
When To Use
- Use this skill when the request is about: android ui test, compose ui test screen, espresso validation android.
- Primary outcome: Validate Android UI behavior with Compose UI tests, Espresso-style checks, screenshot assertions, and accessibility verification.
- Reach for this skill when the missing work is assertions, instrumentation, screenshot capture, or accessibility verification, not product-state design.
- Handoff skills when the scope expands:
android-compose-accessibilityandroid-ui-states-validation
Workflow
- Scope the risk surface: behavior, visual regressions, accessibility semantics, or cross-device interaction.
- Pick the narrowest verification strategy that still catches the likely regressions: instrumentation for behavior, Roborazzi for visuals, or both for high-risk flows.
- Instrument the workflow so failures are actionable rather than just red.
- Run the relevant checks on the showcase apps and packaging outputs.
- Capture any residual risk with explicit follow-up work and owner skills, including handing off to
android-ui-states-validationwhen the state matrix itself is incomplete.
Guardrails
- Prefer reproducible checks in CI over one-off local heroics.
- Keep screenshot tests stable by using deterministic content, fixed themes, and minimal time-based UI churn.
- Fail with a precise remediation path instead of a vague quality gate.
- Keep secrets, signing material, and production credentials out of examples and fixtures.
- Treat performance and security work as engineering tasks with evidence, not folklore.
Anti-Patterns
- Adding more tests without increasing signal.
- Turning screenshot tests into pixel-noise snapshots of unstable surfaces.
- Shipping benchmarks or security scans that no one can reproduce.
- Hard-coding release credentials into build logic.
- Using synthetic metrics with no user-impact interpretation.
Remediation Examples
Choose behavior vs screenshot coverage
composeTestRule.onNodeWithText("Review blocked state").performClick()
composeTestRule.onNodeWithText("Reminder readiness").assertIsDisplayed()
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 92 lines · 24 tokens per session scan A 576f131f9736
android-testing-ui is a skill published in the GitHub repository krutikJain/android-agent-skills (14 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 1,053 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
argent-test-ui-flow
Autonomously test an app UI (iOS or Android) by running interact-screenshot-verify loops using argent MCP tools. Use when testing UI flows, verifying login works, testing navigation, running end-to-end UI test scenarios, manual QA steps, visible UI changes, or visual behavior.
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.
argent-create-flow
Create, record, edit, replay, or repair reusable Argent flow YAML files. Use when the user asks to record or replay a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-flows. Also use before repeating three or more interactions. For one-off UI checks…
argent-ios-device-interact
Drive a physical iPhone through argent. Use when a physical iPhone is involved (a list-devices iOS entry with kind "device") and ONLY then; never for a simulator. For cable, trust, or signing problems read argent-ios-device-setup.