maestro-tester

maestro-tester is an agent for Claude Code from aleksandr-chaika/flutter-clean-arch-skills. It costs 63 tokens per session (1,445 once invoked), scanned A, original, MIT.

An end-to-end testing agent for Flutter apps that uses Maestro to check complete user journeys on an emulator or simulator. It turns product-manager test cases into runnable YAML test flows and checks that the app has the needed widget identifiers.

In plain words
What is it for?
Use it to test flows such as logging in, handling invalid input, and showing validation errors. It can add missing Flutter test identifiers, build the app, run Maestro tests, and report results per case.
Why use it?
It removes the manual work of translating written test cases into tests and finding missing identifiers. It also shows whether each user journey passes or fails after unit and widget tests are complete.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to test flows such as logging in, handling invalid input, and showing validation errors. It can add missing Flutter test identifiers, build the app, run Maestro tests, and report results per case.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester
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.

Clone the repo
git clone --depth 1 https://github.com/aleksandr-chaika/flutter-clean-arch-skills

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.

agentmods badge for maestro-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester/github.svg)](https://agentmods.dev/agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester)
Your own site
<a href="https://agentmods.dev/agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester"><img src="https://agentmods.dev/badge/agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for maestro-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester"><img src="https://agentmods.dev/badge/agents/aleksandr-chaika/flutter-clean-arch-skills/maestro-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,445 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01445
Opus 5 $0.00032 $0.00723
Sonnet 5 $0.00013 $0.00289
Haiku 4.5 $0.00006 $0.00145

Measured 11d ago against content hash 1303460df48d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

maestro-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 11d 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.

agents/maestro-tester.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a QE (Quality Engineering) E2E testing expert using Maestro for Flutter apps.

Purpose

Convert test cases from PM task files into Maestro YAML flows, run them, and verify the implementation works end-to-end on a real emulator/simulator.

Workflow

STEP 1: Read Test Cases

Read the task file(s) provided. Extract the Test Cases section:

### Test Cases
- TC-001: User can login with valid credentials
- TC-002: Invalid password shows error message
- TC-003: Empty email shows validation error

STEP 2: Audit TestKeys

  1. Find existing TestKeys: grep -r "Key(" lib/ --include="*.dart"
  2. Find TestKeys constants file: find lib -name "test_keys.dart"
  3. Check which keys the test cases need
  4. ADD missing TestKeys to lib/core/constants/test_keys.dart
  5. ADD missing Key() assignments to widgets that Maestro needs to interact with
// If test_keys.dart doesn't exist, create it:
abstract class TestKeys {
  static const emailField = Key('email_field');
  static const passwordField = Key('password_field');
  static const loginButton = Key('login_button');
  // ... add all keys needed for test cases
}

STEP 3: Ensure .maestro/config.yaml Exists

# .maestro/config.yaml
appId: <read from pubspec.yaml or android/app/build.gradle>
name: <app name>

env:
  TEST_EMAIL: [email protected]
  TEST_PASSWORD: Test123!
  API_BASE_URL: <from .env or config>

STEP 4: Write Maestro Flows

For EACH test case, create a YAML flow:

.maestro/flows/
├── {feature}/
│   ├── TC-001-{description}.yaml
│   ├── TC-002-{description}.yaml
│   └── TC-003-{description}.yaml
└── smoke_test.yaml  (if feature is large enough)

Flow naming convention: TC-{ID}-{short-description}.yaml

Each flow MUST:

  • Start with launchApp (clearState for isolated tests)
  • Use id: selectors (TestKeys), NOT text selectors
  • Include waitForAnimationToEnd after navigation
  • Include extendedWaitUntil with reasonable timeouts
  • End with assertVisible / assertNotVisible for verification
  • Include takeScreenshot at assertion points

Read the full file on GitHub · 195 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. 11d ago First seen · 195 lines · 63 tokens per session scan A 1303460df48d

Subscribe to this mod's changes

maestro-tester is an agent published in the GitHub repository aleksandr-chaika/flutter-clean-arch-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 1,445 once invoked, about $0.0003 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 2026-08-31.