Agentic Workflow Pattern Standard multi agent pipeline for implementation tasks. Architecture Principles Use run in background: true for all agents to keep main context minimal Use Task tool (never TaskOutput ) to avoid receiving full agent transcripts Agents write outputs to .claude/cache/agents/<stage / for injection into subsequent agents Main conversation is pure orchestration — no heavy lifting, only coordination Workflow Stages 1. Research Agent Enforce NIA as the research layer Output: Research findings 2. Planning Agent Receives: Research agent output as context Output: Implementation plan 3. Validation Agent Reviews plan against research Output: Validated plan with amendments 4. Implementation Agent Receives: Validated plan + research context TDD : Failing tests first Output: Implementation + tests 5. Review Agent Cross references all artifacts Confirms tests pass Output: Review summary Agent Progress Monitoring Stuck detection: 1. Progress reminders stop arriving 2. Task output file size stops growing 3. Expected output file not created after reasonable time Directory Structure Key Rules 1. Never use TaskOutput floods context with 70k+ token transcripts 2. Always run in background=true isolates agent context 3. File based handoff each agent reads previous agent's output file 4. Poll, don't block check file system for outputs, don't wait 5. TDD in implementation failing tests first, then make them pass Source Session 2026 01 01: SDK Phase 3 implementation using this pattern

agentic-workflow