Run an end-to-end browser test of Alethical as a real user — after a feature lands, on demand ("browser-test this", "drive the app", "test it like a user"), or before calling frontend work done. Spawns a FRESH-context agent on a cheap model that knows nothing about the implementation, drives the running app through a browser in scripted user stories or free exploration, and reports what breaks. Also owns the on-demand Playwright checks (just e2e) and the path from a stable story to a Playwright spec.