maestro-testing

maestro-testing is a skill for Claude Code from eagleisbatman/maestro-skill. It costs 176 tokens per session (5,841 once invoked), scanned C, original, MIT.

A helper for creating and maintaining Maestro test flows for mobile and web applications. Maestro flows are YAML files that describe actions and checks a test should perform, such as opening a screen and verifying text.

In plain words
What is it for?
Use it to generate or edit tests for Android, iOS, and web apps, create flows from requirements or user stories, choose reliable element selectors, produce reports, and connect tests to continuous integration.
Why use it?
It reduces the work of writing, debugging, and organising end-to-end tests that operate through an app's user interface.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the maestro-testing plugin — 1 skill shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add eagleisbatman/maestro-skill
Claude Code
/plugin install maestro-testing

Made for: Claude Code.

Or install maestro-testing, the plugin that ships this one along with the rest of its 1 skill.

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 maestro-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/eagleisbatman/maestro-skill/maestro-testing.svg)](https://agentmods.dev/skills/eagleisbatman/maestro-skill/maestro-testing)
Your own site
<a href="https://agentmods.dev/skills/eagleisbatman/maestro-skill/maestro-testing"><img src="https://agentmods.dev/badge/skills/eagleisbatman/maestro-skill/maestro-testing.svg" alt="Measured on agentmods" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,841 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 5.1 $0.00176 $0.05841
Opus 5 $0.00088 $0.02920
Sonnet 5 $0.00035 $0.01168
Haiku 4.5 $0.00018 $0.00584

Measured 6d ago against content hash dfeca425da59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

maestro-testing 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 6d 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/maestro-testing/SKILL.md · 623 lines

How it starts

The opening of the file, as written. The whole thing — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Maestro Testing Skill

Generate production-ready Maestro YAML test flows for any mobile or web app. This skill covers flow generation, selector strategy, report generation, CI/CD integration, QA workflows, and MCP-powered AI-assisted testing.

Prerequisites & Installation

Maestro requires Java 17+ and installs with a single command — zero other dependencies:

curl -fsSL "https://get.maestro.mobile.dev" | bash
  • Android: Emulator or physical device with USB debugging (API 26+)
  • iOS: Xcode with iOS Simulator (macOS only, simulator builds only — no real devices)
  • Web: No additional setup — Maestro auto-downloads Chromium on first run

Before Generating Flows

Read the appropriate reference file for the user's framework:

  • React Native / Expo${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/react-native.md
  • Flutter${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/flutter.md
  • Native Android (Kotlin/Java/Jetpack Compose)${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/native-android.md
  • Native iOS (Swift/SwiftUI/UIKit)${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/native-ios.md
  • Hybrid (Capacitor/Ionic/Cordova/PWA)${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/hybrid.md
  • Web Desktop Browser → use url: instead of appId:, same commands. No separate reference needed.
  • QA workflows, reports, CI/CD${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/qa-workflows.md

If framework is unknown, ask. Default to ${CLAUDE_PLUGIN_ROOT}/skills/maestro-testing/references/react-native.md.


1. Project Structure

.maestro/
├── config.yaml                 # Workspace-level config
├── flows/
│   ├── auth/
│   │   ├── login.yaml
│   │   ├── login-invalid.yaml
│   │   ├── signup.yaml
│   │   └── logout.yaml
│   ├── onboarding/
│   │   └── first-launch.yaml
│   ├── core/
│   │   ├── create-item.yaml
│   │   ├── edit-item.yaml
│   │   └── delete-item.yaml
│   ├── navigation/
│   │   └── tab-navigation.yaml
│   ├── edge-cases/
│   │   ├── no-network.yaml
│   │   ├── empty-state.yaml
│   │   ├── orientation-change.yaml
│   │   └── long-text-input.yaml
│   └── smoke/
│       └── critical-path.yaml
├── subflows/                    # Reusable — NOT run as standalone tests
│   ├── login.yaml
│   ├── navigate-to.yaml
│   └── teardown.yaml
├── scripts/
│   ├── setup.js
│   ├── generate-data.js
│   ├── page-objects.js          # Page Object Model selectors
│   └── run-tests.sh
└── media/
    ├── test-photo.png
    └── test-video.mp4

Read the full file on GitHub · 623 lines

Files

What ships with it

6 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.

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. 6d ago First seen · 623 lines · 176 tokens per session scan C dfeca425da59

Subscribe to this mod's changes

maestro-testing is a skill published in the GitHub repository eagleisbatman/maestro-skill (3 stars, last pushed 6mo ago), licensed MIT. It adds 176 tokens to every session and 5,841 once invoked, about $0.0009 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

mobile-automation

MCP (dart-mcp + Marionette) を使ったFlutterアプリのE2E自動化・UI検証ガイド。シミュレーターでのUI動作確認、モックプレビュー検証、Bridge経由のE2Eテスト、スクリーンショット撮影など、アプリの動作検証が必要なときに使う。「動作確認して」「UIを検証して」「E2Eテスト」「シミュレーターで確認」「モックで確認」と言われたときや、UI変更後の検証フェーズで使用すること。.

K9i-0/ccpocket · 138 tokens

test-flutter

Flutter App のテスト実行・静的解析・フォーマット・テスト記述ガイド.

K9i-0/ccpocket · 26 tokens

zmr-mobile-testing

Use when testing mobile apps with Zeno Mobile Runner, integrating app-local .zmr setup, driving Android or iOS simulator scenarios, using JSON-RPC or MCP agent sessions, exporting traces, or comparing mobile runner benchmarks.

johnmikel/zeno-mobile-runner · 50 tokens

cloudx-integrate

Integrate the CloudX SDK into a publisher app on any supported platform (Android, iOS, React Native, Flutter, Unity). Use when asked to integrate, add, install, or set up CloudX, CloudX ads, or CloudX mediation in an app, including alongside or replacing an existing mediation stack such as AppLovin MAX, LevelPlay, or…

cloudx-io/cloudx-sdk-agents · 82 tokens

aco

Drive a live Appium session from the shell with the aco CLI. Use when the user wants to interact with a running mobile app on an iOS simulator, Android emulator, or connected real device — tap, swipe, type, screenshot, read the screen/page source, find UI elements, switch to a WebView context, or call iOS/Android…

tai2/aco · 111 tokens

android-e2e-readiness

Use when Android mobile E2E flows are flaky, Compose and View screens disagree with automation, hybrid screens are ambiguous, retries hide the real issue, or the team keeps collapsing the problem to selector-vs-timing without checking Android-specific readiness contracts.

shenyuexin/mobile-e2e-mcp · 57 tokens