cc-harness

Trigger a standalone evaluation of the current application using the skeptical evaluator agent

Show current harness session status — iteration count, scores, feature progress, and session metrics

Start a harnessed development session with planner → generator → evaluator loop for autonomous multi-hour coding

Use PROACTIVELY after generator completes a feature. Skeptical QA agent that tests the live application via Playwright/browser, grades against sprint contracts and quality criteria. Deliberately resistant to approving mediocre work.

Use when building features from a harness spec. Implements features iteratively one at a time, writes sprint contracts, self-evaluates, commits to git, and hands off to the evaluator via files.

Use PROACTIVELY when starting a harnessed build. Converts brief 1-4 sentence prompts into ambitious, detailed product specs. Focuses on product context and high-level technical design, not implementation details.

Use when running long coding sessions that approach context limits - provides strategies for compaction vs context resets, structured handoffs, and managing context anxiety across model versions

Use when building complex applications autonomously - orchestrates a generator-evaluator iteration loop with planner, generator, and evaluator agents for long-running multi-hour coding sessions

Use when optimizing or simplifying a multi-agent harness - guides systematic removal of components as models improve, evaluator calibration, and prompt engineering for grading criteria

3 hooks across 3 events