Test Execution Agent — Testing & QA agent for Claude Code
Single execution agent for every playwright-bdd test test-writer produces — browser tests (WAY 1) and API tests (WAY 2).
How to install Test Execution Agent
Installs to ~/.claude/agents/ghassenazzouz-claude-qa-agent-test-execution-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/GhassenAZZOUZ/claude-qa-agent/HEAD/.claude/agents/test-execution-agent.md -o ~/.claude/agents/ghassenazzouz-claude-qa-agent-test-execution-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Test Execution Agent does
name: test-execution-agent description: Single execution agent for every `playwright-bdd` test `test-writer` produces — browser tests (WAY 1) and API tests (WAY 2). Runs real `npx playwright test`, not a live-driven MCP session. Replaces the former playwright-navigator and api-executor. tools: Bash, Read, Write
test-execution-agent
You are the single test execution agent. Every test you run was written by `test-writer` as a `.feature` + `.steps.ts` pair — you never drive a browser or
Alternatives in Testing & QA
- Pencil UI Designer — Use this agent when you need Pencil-based design workflows: atomic designer actions, MCP tools, and spec-drive 635 ★
- Review Test Quality — Reviews test code for behavior-driven quality and completeness: whether tests verify real behavior vs chasing 432 ★
- QA Manual Tester — Use this agent when you need to perform manual quality assurance testing through browser interactions 394 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Manual QA
Use when a change needs to be exercised in a real running app — not unit tests, but a human-style check of the
Manual Tester Agent
Use this agent to test the live application under test the way a human QA would - persona-driven exploration (
Developers
VP of Engineering who leads six skills — superpowers (engineering protocols), context7 (live library docs), mc
E2e Test Writer
E2E spec author — explores a live app via Playwright MCP (browser_snapshot → interact → assert), authors durab
MCP Dogfooder
Drives the shipped MCP debugger tools as a real user would — launch, breakpoints, stepping, locals, object exp
Execution Agent
Autonomously executes a single subtask in its own worktree. Reads plan + subtask spec + declared context, impl
Related Skills
BDD Init
Создать .bdd-config.yaml + feature-директории в текущем репо. Автодетект стека. Usage — /bdd-init --stack pyt
E2e Test Writer
Write end-to-end tests using Playwright or Cypress
Leapfrog MCP
Multi-session browser MCP server -- 15 parallel isolated Chromium sessions so multiple Claude Code terminals c