What is mobile-e2e-tester?

An end-to-end tester for Android apps that checks user-visible behavior on an already running emulator or physical device.

Launching the installed app, following specified test scenarios, scrolling through screens, checking logcat after failures, and reporting pass or fail results.

It tests the app as a user would and reports failures without changing the application code or requiring the tester to install the app or start the device.

How deltazefiro/Amarok-Hider configures Claude Code

About the project

Amarok-Hider is an Android privacy tool that makes selected files and apps less visible by changing how the system identifies or displays them, rather than encrypting their contents. It is for people who want quick protection from casual snooping, with optional root-based features for deeper app hiding.

deltazefiro/Amarok-Hider · 3,235 stars · on GitHub · deltazefiro.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to deltazefiro/Amarok-Hider. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/deltazefiro/Amarok-Hider/main/.claude/agents/mobile-e2e-tester.md

Clone the repo

git clone --depth 1 https://github.com/deltazefiro/Amarok-Hider

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/deltazefiro/amarok-hider/mobile-e2e-tester.svg)](https://agentmods.dev/agents/deltazefiro/amarok-hider/mobile-e2e-tester)

Your own site

<a href="https://agentmods.dev/agents/deltazefiro/amarok-hider/mobile-e2e-tester"><img src="https://agentmods.dev/badge/agents/deltazefiro/amarok-hider/mobile-e2e-tester.svg" alt="Measured on agentmods" height="20"></a>

Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 517 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.00517
Opus 5	$0.00039	$0.00259
Sonnet 5	$0.00016	$0.00103
Haiku 4.5	$0.00008	$0.00052

Measured 8d ago against content hash 027d98182a8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mobile-e2e-tester 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 8d 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.

.claude/agents/mobile-e2e-tester.md · 37 lines

What it actually says

mobile-e2e-tester

You are an expert Android QA engineer performing automated end-to-end testing.

Guidelines

Test user-facing behavior (black-box approach), NOT implementation details or debugging.
If input not responding or screen returns, perhaps a crash occurred, check logcat.
Always use filters when fetching logcat to avoid excessive data.
Keep your testing process simple and efficient. If stuck, fail fast and report.
NEVER modify the code.
Scrolling through long lists: Use large swipes (1000-1200px). Partial element visibility is normal. Only fail after 10+ scrolls with no new elements.

Procedure

Assertion: An active emulator or physical device must be running with the target APK pre-installed. Do not perform installation or emulator startup. If these requirements are not met, just return with fail message.

Create backlog file: Create ./tmp/e2e_test_backlog.md (tmp in the project folder, you do not have access to /tmp).
Call mobile_list_available_devices to identify the device ID.
Launch app: adb shell monkey -p deltazero.amarok.foss -c android.intent.category.LAUNCHER 1 (use .foss suffix for FOSS builds)
Test with mobile mcp:
- Run sleep 1 to wait for UI to settle after each action
- Prefer adb shell input text "..." over mobile_type_keys for text input. Avoid backspace loops.
- Use screenshots ONLY for verification. Do NOT use mobile_list_elements_on_screen (unreliable for custom views)
- Update backlog every several steps to track your progress, test blockers, and observations. Update it as you work.

Output

For the failure cases, provide: bug report (both functional and visual), steps to reproduce, file paths to screenshots, optional logcat snippets
On success, provide: Screenshot file paths as evidence of successful test completion

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.

8d ago First seen · 37 lines · 79 tokens per session scan A 027d98182a8f

Subscribe to this mod's changes

mobile-e2e-tester is an agent published in the GitHub repository deltazefiro/Amarok-Hider (3,235 stars, last pushed 27d ago), licensed Apache-2.0. It adds 79 tokens to every session and 517 once invoked, about $0.0004 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.

E2E testing Mobile Testing android android-application file-hider hider privacy-protection

ui-test-writer

UI test implementation specialist. Creates Compose UI tests and SwiftUI tests for screens. Android: Compose Testing + Espresso. iOS: XCUITest + ViewInspector. Tests loading/error/success states, interactions, accessibility.

ahmed3elshaer/everything-claude-code-mobile · 49 tokens

android-testing-ui

Validate Android UI behavior with Compose UI tests, Espresso-style checks, screenshot assertions, and accessibility verification.

krutikJain/android-agent-skills · 24 tokens

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…

simiancraft/simiancraft-skills · 247 tokens

mobile-mobile-qa

Mobile QA engineer that tests mobile applications, performs device testing, and ensures quality.

MonumentalSystems/Atlas-Agent-Teams · 20 tokens

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…

uwuclxdy/agenticat · 73 tokens

mobile-pr-test-analyzer

Use this agent to review test coverage and test quality for a mobile PR diff (Android/Kotlin, iOS/Swift, or KMP) — missing coverage for new/changed behavior, untested edge cases and error paths, and tests that don't actually exercise the code they claim to. Feed it the PR intent, full diff, changed-file list, and the…

Abdallah-Abdelazim/mobile-pr-review-plugin · 103 tokens

Amarok-Hider: Agent for Claude Code