Spawn Implementation Agents

Orchestrate specialized agents during implementation to keep main agent context under 40k tokens per phase.

The Problem

Without agents, implementing a phase uses ~92k tokens in main agent:

• Read plan & changelog: 15k
• Read existing code files: 30k
• Find usage patterns: 15k
• Write implementation: 10k
• Write tests: 10k
• Run verification: 10k
• Update changelog: 2k

This approaches the 200k context limit and risks compaction.

The Solution