subagent official · GitHub

Playwright Tester Mode — GitHub Copilot subagent for Playwright tests

Q: How do I install Playwright Tester Mode in GitHub Copilot?

Place the subagent file at `.github/agents/playwright-tester.agent.md` inside your project repository.

A GitHub Copilot subagent that walks the site through Playwright MCP first, then writes and runs TypeScript tests.

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓

.github/agents/playwright-tester.agent.md

Open on GitHub

What Playwright Tester Mode does

Playwright Tester Mode sets the order of work for browser testing. The agent opens the site through Playwright MCP, takes a page snapshot and maps the key user flows. No code is written before that step, so locators come from the real markup instead of a guess.

After exploring, it generates TypeScript tests, runs them, diagnoses failures and iterates until the run is stable. Asked to improve existing tests, it navigates to the URL, reads the snapshot and fixes locators; a running dev server may be needed first. It closes with a short summary of what the tests cover and how the generated code is structured.

The agent carries tools such as runTests, testFailure, findTestFiles and playwright, and runs on Claude. The file goes to .github/agents/playwright-tester.agent.md, so without Playwright MCP and a working project setup the agent stalls at the very first navigation step.

What it helps with

map key user flows before writing any tests
pick locators from a real page snapshot
generate TypeScript tests from scratch
diagnose failing runs and make tests stable
summarise test coverage and file structure

Example prompts for the agent

Explore the site with Playwright MCP and write TypeScript tests for login
Improve the existing tests: open the checkout page and fix the locators
Run the tests, diagnose the failures and fix them

How to install Playwright Tester Mode

Manually: put the files in place

.github/agents/playwright-tester.agent.md

Manually: put the files in place

.claude/agents/playwright-tester.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention. Copilot names tools its own way in the tools field: remove it or rewrite it for Claude Code

Manually: put the files in place

.codex/agents/playwright-tester.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Manually: put the files in place

.cursor/agents/playwright-tester.md

Cursor also reads .claude/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about Playwright Tester Mode

How do I install Playwright Tester Mode in GitHub Copilot?

Place the subagent file at .github/agents/playwright-tester.agent.md inside your project repository.

What does Playwright Tester Mode do?

It opens the site through Playwright MCP, maps the key flows, then writes TypeScript tests, runs them and refines the code until the run is stable.

What does the subagent need to work?

Playwright MCP for navigation and page snapshots. A running dev server may be required to verify the tests.

Source text

playwright-tester.agent.md · MIT

---
description: "Testing mode for Playwright tests"
name: "Playwright Tester Mode"
tools: ["changes", "codebase", "edit/editFiles", "fetch", "findTestFiles", "problems", "runCommands", "runTasks", "runTests", "search", "searchResults", "terminalLastCommand", "terminalSelection", "testFailure", "playwright"]
model: Claude Sonnet 4
---

## Core Responsibilities

1.  **Website Exploration**: Use the Playwright MCP to navigate to the website, take a page snapshot and analyze the key functionalities. Do not generate any code until you have explored the website and identified the key user flows by navigating to the site like a user would.
2.  **Test Improvements**: When asked to improve tests use the Playwright MCP to navigate to the URL and view the page snapshot. Use the snapshot to identify the correct locators for the tests. You may need to run the development server first.
3.  **Test Generation**: Once you have finished exploring the site, start writing well-structured and maintainable Playwright tests using TypeScript based on what you have explored.
4.  **Test Execution & Refinement**: Run the generated tests, diagnose any failures, and iterate on the code until all tests pass reliably.
5.  **Documentation**: Provide clear summaries of the functionalities tested and the structure of the generated tests.

Similar subagents

All subagents for Testing and QA →

playwright-e2e-testing fugazi A skill for writing and maintaining Playwright E2E specs in TypeScript: user flows, forms, auth, API mocking and visual comparisons. CX Codex +1 615installs playwright-defect-tracking-cursorrules-prompt-file PatrickJS A Cursor rule that makes the agent write Playwright tests tied to manual case IDs, with screenshots and logs as defect evidence. ★ 41,011repo stars playwright-skill testdino.com Supplies the agent with 79 reference guides for Playwright 1.64 across TypeScript and JavaScript. Helps write tests, investigate CI failures, configure mocking, and stabilize flaky suites. CX Codex +1 6,200installs playwright-expert https://github.com/Jeffallan Sets up Playwright E2E testing infrastructure, writes Page Object Model classes, and troubleshoots flaky tests using trace inspection. CX Codex +1 5,300installs visual-regression-tester patricio0312rev This skill sets up visual regression testing: it captures screenshots, compares them against baselines and flags unintended UI changes. CX Codex +1 330installs playwright-cli microsoft A skill that hands your agent a browser: open a page, click elements, grab a snapshot, and work with Playwright tests. CX Codex +1 195,700installs

From the same set732

The whole set →