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 skills/guillemroca/agent-skills-android/android-e2e-verificationnpx skills add GuillemRoca/agent-skills-android --skill android-e2e-verificationgit 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/skills/guillemroca/agent-skills-android/android-e2e-verification)<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/android-e2e-verification"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/android-e2e-verification.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 | $0.00065 | $0.01768 |
| Opus 5 | $0.00032 | $0.00884 |
| Sonnet 5 | $0.00013 | $0.00354 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade C, and why
android-e2e-verification scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL "https://get.maestro.mobile.dev" | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL "https://get.maestro.mobile.dev" | bash How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Android E2E Verification (Maestro)
Overview
"It compiles and the unit tests pass" is not proof that a feature works. This skill closes the loop: every feature slice gets a Maestro flow — a YAML file of user actions and assertions derived from the spec's acceptance criteria — that runs black-box against the installed app. Implement, build, run the flow, watch it pass (or fix and re-run). The flow is committed next to the code, so the acceptance criterion stays executable forever.
Maestro drives the app over adb with no app-code changes, no test hooks, and no build instrumentation — it works on release builds and survives refactors that would break selector-heavy tests.
When to Use
- Completing any feature slice with a user-visible flow (see
incremental-implementation) - Turning a spec's acceptance criteria into executable checks (see
spec-driven-development) - Verifying a bug fix actually fixes the user-facing behavior, not just the unit under test
- Regression-protecting critical journeys (login, checkout, sync) in CI
- Smoke-testing release candidates before rollout (see
shipping-and-launch)
Skip when: The change has no runtime UI surface (pure data-layer refactor, build config) — unit/integration tests are the right layer. Don't use Maestro to test in-app logic permutations; that's what ViewModel and repository tests are for (see test-driven-development).
Core Process
Step 1: Install and Probe
- Install Maestro (single binary, Java 17+):
# Pin the version so CI and local runs agree
export MAESTRO_VERSION=2.6.1
curl -fsSL "https://get.maestro.mobile.dev" | bash
# or: brew install mobile-dev-inc/tap/maestro
maestro --version # probe availability
If Maestro is unavailable in the environment, say so explicitly and fall back to Compose/Espresso tests plus android screen capture verification — never silently skip E2E verification.
Step 2: Write the Flow From Acceptance Criteria — Before Implementing
- Translate each acceptance criterion into a flow under
.maestro/, named after the slice:
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.
- 4d ago First seen · 156 lines · 65 tokens per session scan C 6d0bd3fe5872
android-e2e-verification is a skill published in the GitHub repository GuillemRoca/agent-skills-android (2 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,768 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
t-flutter-demo-run
Run and repair one Android Patrol user-story demo file.
t-flutter-demo-accept
Accept Android Patrol demos against their user stories and execution evidence.
t-flutter-demo-run-all
Run all Android Patrol user-story demo files with resumable checkpoints.
e2e-testing-mobile
Plans, generates, runs, and heals end-to-end tests for Expo and React Native mobile apps using Maestro (the 2026 standard for RN E2E, adopted by Meta, Microsoft, and DoorDash, and integrated with Expo via EAS Workflows). Drives a spec-first YAML-flow loop, proposes testID source diffs (never accessibilityLabel reuse)…
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…
capturing-proof
This skill should be used when the user asks to "capture proof", "record a demo of this feature", "make a video showing it works", "record the flow for the PR", "generate a PR body", "capture screenshots for the PR", "proof-capture", or when a verified feature needs PR-ready proof artifacts (video + numbered…