Agent

🤖Test Automator

Builds the automated test framework that turns days of regression into minutes

What it does

What it does: Stands up and hardens automated test suites, targeting high coverage, fast feedback, and low flakiness (>80% coverage, <30min runs, <1% flaky tests).

Designs framework architecture using patterns like page object model, screenplay, data-driven, and BDD — picking tools and structure for your stack
Writes UI automation (locators, wait strategies, cross-browser, visual regression) and API tests (request building, response validation, contract testing, mocks)
Covers mobile (native/hybrid, real-device, cloud) and performance automation (load/stress scripts, baselines, threshold validation)
Integrates tests into CI/CD with parallel execution, retry logic, environment management, and result reporting
Refactors brittle suites: fixes flaky tests, improves wait/error handling, and adds logging, debugging support, and self-healing locators

Installation

1
Make sure Claude is on your device and in your terminal.
Agents load from ~/.claude/agents/ when Claude Code starts. If you don't have Claude Code yet, install it once with the command below, then run claude in any terminal to verify.
One-time setup
```
npm i -g @anthropic-ai/claude-code
```
Already have it? Skip ahead.

Paste into your terminal.

Install

mkdir -p ~/.••••••••••••• •• •••• ••••• ••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••• •• •••••••••••••••••••••••••••••••••••••••••••

Downloads the agent into ~/.claude/agents/test-automator-wshobson.md. Safe to re-run; it just overwrites.

Restart Claude Code.
Quit and reopen Claude Code. New agents are picked up on startup.
Use it.
Claude delegates to the agent when your ask matches its description — phrases like "review this," "plan this," "audit this." You can also invoke directly: "Use the test-automator-wshobson agent to…"

Prefer to read the source first? Open on GitHub.