tdd-migrate

Orchestrate TDD migrations with agents doing all work. Main context stays clean. Main context = orchestration only Agents do ALL work Parallel where independent Review after each major step Write a YAML plan file to thoughts/shared/plans/ -tdd.yaml : For each item, launch ONE kraken that does full TDD: If critic/validator found issues: Update ledger with completed work. Resulted in: - "Port X from Python to TypeScript" - "Create N adapters following existing pattern" - "Migrate module to new architecture" - "TDD implementation of multiple similar items" - source_path : Path to analyze (existing code) - target_path : Where to create new code - pattern : Reference file/pattern to follow - items : Comma-separated list of things to create - Main context = orchestration only - Never read files directly (use scout) - Never implement directly (use kraken/spark) - Never run tests directly (use validator) - Only pipe context and coordinate - Agents do ALL work Task Agent Explore/analyze scout Write tests + implement kraken Quick fixes spark Run tests/validate validator Code review critic - Parallel where independent - All items can be implemented in parallel if independent - Review + QLTY run in parallel - TLDR analysis runs in parallel with planning - Review after each major step - After implementation: critic reviews - After fixes: validator re-validates - 5 parallel kraken agents -...