android-e2e-verification

android-e2e-verification is a skill for Claude Code, Codex from GuillemRoca/agent-skills-android. It costs 65 tokens per session (1,768 once invoked), scanned C, original, MIT.

A way to check an Android app from the outside by replaying user actions and checking the results. Maestro flows are YAML files that turn acceptance criteria—the conditions a feature must meet—into repeatable tests.

In plain words
What is it for?
Testing login, checkout, syncing, bug fixes, release builds, and other visible app flows locally or in continuous integration.
Why use it?
A successful build or unit test does not prove that a user-facing feature works in the installed app. These checks verify complete journeys, including behavior across the app’s interface.

Skill for Claude CodeCodex

Part of the agent-skills-android plugin — 29 skills, 7 commands, 3 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/guillemroca/agent-skills-android/android-e2e-verification
Any agent
npx skills add GuillemRoca/agent-skills-android --skill android-e2e-verification
Clone the repo
git clone --depth 1 https://github.com/GuillemRoca/agent-skills-android

Made for: Claude Code, Codex.

Or install agent-skills-android, the plugin that ships this one along with the rest of its 29 skills, 7 commands, 3 agents, 1 hook.

Wrote 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.

agentmods badge for android-e2e-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/android-e2e-verification.svg)](https://agentmods.dev/skills/guillemroca/agent-skills-android/android-e2e-verification)
Your own site
<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>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 6d0bd3fe5872, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
skills/android-e2e-verification/SKILL.md · 156 lines

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

  1. 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

  1. Translate each acceptance criterion into a flow under .maestro/, named after the slice:

Read the full file on GitHub · 156 lines

Changes

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.

  1. 4d ago First seen · 156 lines · 65 tokens per session scan C 6d0bd3fe5872

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories