What problem does it solve? AI coding agents lack structured engineering workflows and fast, stateful browser automation, leading to unreviewed plans, untested ships, and slow multi-second browser commands that lose login state between calls. ## Core Features & Use Cases - Workflow Skills: Over 20 specialist skills covering the full development lifecycle — plan reviews (CEO, engineering, design), PR review, systematic debugging, QA with a real browser, shipping, security audits, and retrospectives. - Persistent Headless Browser: A compiled CLI talks to a long-lived Chromium daemon over localhost HTTP, giving ~100ms commands after the first call, with ref-based element selection via the accessibility tree and cookie import from real browsers. - Safety Guardrails: Skills like /careful, /freeze, and /guard warn or block destructive commands and restrict edits to specific directories. - Use Case: A developer runs /plan-eng-review to lock architecture before coding, /review to catch bugs that pass CI, then /ship to run tests, verify plan completion, and open a PR — all with cross-model second opinions from Codex or Claude subagents. ## Quick Start Ask the agent to run the /office-hours skill to reframe your product idea before writing any code.