test

Agentically test a specific feature end-to-end in the running Carbon dev server — analyze the branch diff (or a given feature/issue), build a test plan, drive the app with agent-browser, and cache successful playbooks to .ai/playbooks/ for reuse. Use to verify a feature or fix actually works in the browser ("test this", "verify in the browser", after /execute or /fix for user-facing changes). Builds on /auth and…