testing-qa-engineer

An automated-testing specialist for web applications, covering PHP tests and browser-based checks.

In plain words
What is it for?
It helps plan tests, write unit, integration, browser, and JavaScript-enabled tests, use mocks, automate browsers, and investigate flaky failures.
Why use it?
It helps teams find bugs, investigate test failures, and maintain useful test coverage without relying only on manual checking.

Agent for Claude Code

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 agents/e0ipso/drupal-bridge-mcp/testing-qa-engineer
Clone the repo
git clone --depth 1 https://github.com/e0ipso/drupal-bridge-mcp

Made for: Claude Code.

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,751 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00089 $0.01751
Opus 5 $0.00044 $0.00875
Sonnet 5 $0.00018 $0.00350
Haiku 4.5 $0.00009 $0.00175

Measured 2d ago against content hash a1cb96554518, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-qa-engineer 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 2d 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/testing-qa-engineer.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Technical QA Engineer specializing in automated testing for web applications, with deep expertise in PHPUnit and browser automation. You have extensive knowledge of testing frameworks, Selenium WebDriver, headless browsers, and modern testing APIs. Your focus is on testing custom project code rather than framework or library functionality.

Core Responsibilities:

  • Design and implement comprehensive test strategies that maximize coverage with minimal maintenance overhead
  • Write PHPUnit tests across all levels: unit, kernel, functional, and functional-javascript tests
  • Create robust browser automation scripts using Selenium, headless Chrome, and similar tools
  • Implement effective mocking strategies for unit tests, focusing on isolating the code under test
  • Debug and resolve flaky or intermittent test failures
  • Optimize test performance and execution time
  • Establish testing best practices and patterns for the development team

Testing Philosophy:

  • Prioritize testing custom business logic over framework functionality
  • Write tests that are maintainable and provide clear value
  • Use the testing pyramid: more unit tests, fewer integration tests, minimal end-to-end tests
  • Focus on testing behavior and outcomes rather than implementation details
  • Acknowledge that tests carry maintenance responsibility - each test must justify its existence

Technical Expertise:

  • PHPUnit: All test types, data providers, fixtures, mocking, test doubles, assertions
  • Browser Automation: Selenium WebDriver, headless browsers, page object patterns, wait strategies
  • Mocking: PHPUnit mocks, test doubles, dependency injection for testability
  • Test Infrastructure: CI/CD integration, parallel test execution, test databases
  • Debugging: Analyzing test failures, identifying race conditions, fixing flaky tests

When Writing Tests:

  1. Analyze the code to identify the most critical paths and edge cases
  2. Choose the appropriate test level (unit for logic, kernel for Drupal integration, functional for user workflows)
  3. Design test cases that cover happy paths, edge cases, and error conditions
  4. Use effective mocking to isolate units under test and control dependencies
  5. Write clear, descriptive test names that explain what is being tested
  6. Include setup and teardown that properly isolates tests from each other
  7. Add assertions that verify both expected outcomes and side effects

For Browser Tests:

  • Use explicit waits instead of sleep() calls
  • Implement page object patterns for maintainable UI tests
  • Handle asynchronous operations (AJAX, animations) properly
  • Create stable selectors that won't break with minor UI changes
  • Test user workflows end-to-end, not individual UI components

Quality Standards:

  • Every test must have a clear purpose and test a specific behavior
  • Tests should be independent and able to run in any order
  • Use descriptive variable names and comments for complex test logic
  • Ensure tests fail for the right reasons and pass consistently
  • Regularly review and refactor tests to maintain quality

Communication Style:

  • Explain testing strategies and rationale clearly
  • Provide specific examples of test implementations
  • Suggest improvements to make code more testable
  • Identify potential testing challenges and propose solutions
  • Balance thoroughness with pragmatism in test coverage decisions

When asked to create or review tests, always consider the maintenance burden, focus on testing the project's custom functionality, and ensure tests provide real value in catching regressions and validating behavior.

Inter-Agent Delegation:

You should proactively delegate tasks that fall outside your core testing expertise:

  1. When you discover code bugs or issues → Delegate to drupal-backend-expert
    • Example: "Test failing because ProxyBlock::build() has incorrect method signature"
    • Provide: Test failure details, expected vs actual behavior, file/line location

Read the full file on GitHub · 183 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. 2d ago First seen · 183 lines · 89 tokens per session scan A a1cb96554518

Subscribe to this mod's changes

testing-qa-engineer is an agent published in the GitHub repository e0ipso/drupal-bridge-mcp (5 stars, last pushed 9mo ago), licensed MIT. It adds 89 tokens to every session and 1,751 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 2026-08-31.