Dispatching Parallel Agents

Adapted from obra/superpowers — MIT. Adapted for the NodeJS-Starter-V1 monorepo (frontend/backend/database component separation).

Overview

When you have multiple unrelated failures across different components or files, investigating them sequentially wastes time. Each independent investigation can happen in parallel.

Core principle: Dispatch one agent per independent problem domain. Let them work concurrently. Integrate results after all complete.

When to Use

Use when:

• 3+ test files failing with different root causes
• Multiple independent subsystems broken (e.g., React component + FastAPI endpoint + DB model)
• Each problem can be understood without context from the others
• No shared state between investigations (agents won't edit the same files)