Use when executing multi-wave engineering work needing strict TDD, bug-capture/fix split, quality gates, and orchestrated teams with per-agent Opus-advisor / Sonnet-executor model routing.
Use as the first phase of a wave. Drafts brutal, testable acceptance criteria for a feature. Each AC must be falsifiable by a real-world test. Output written to .wave/ac.md.
Use after AC and before RED for any wave that ships UI. Performs component API audit against installed dist files, produces per-route mockup, defines visual ACs, flags design-system gaps. Output written to .wave/dr.md.
Use after RED is verified failing. Writes the minimum code to make RED tests pass, then verifies on a live stack with Playwright screenshots before any hand-off. Implements the verify-before-scan rule.
Use after DR and before any production code is written. Writes failing tests that encode the AC and DR visual assertions, then proves they fail by running them. RED phase of TDD — strict, no exceptions.
Use only after the user has approved the GREEN screenshot. Performs True End-to-End Testing across backend, frontend, DB, and external services with computed-style and boundingBox assertions, producing the final wave evidence pack.
Use when shipping a feature end-to-end. Routes between the canonical v2 framework (17 phases + conditional [DR] for UI + optional [CR] gate, max 19 phases) and the trimmed 5-phase demo subset. Invoked by /wave-start and /wave-start --demo. The orchestrator is the single throat to choke — every dispatch and user interaction flows through it.