Playwright appears three times. One loadout has the agent load every UI change in a real browser through Playwright MCP and fail on console errors before it says done. One is for the test suite itself, including Playwright's planner, generator and healer agents: role-based locators, web-first assertions, no fixed waits. The third drives an Electron app through Playwright's Electron support, with assertions on the sandbox, the preload API and IPC validation.
Every one installs for Claude Code, Codex CLI, Cursor, Gemini CLI, Antigravity CLI and GitHub Copilot unless its card says otherwise.
Make the agent load every UI change in a real browser via Playwright MCP, exercise it, fail on console or network errors and attach screenshots at two widths.
Playwright tests that drive the real Electron app: secure webPreferences, no Node in the renderer, IPC round trips, input validation and blocked navigation.
Rules for agents writing and healing Playwright tests, including Playwright's test agents: role locators, web-first assertions, no sleeps, never weaken a test to pass.
Looking for something narrower? Search within Playwright or filter everything.