Multi-Agent Architecture Patterns

Multi-agent architectures distribute work across multiple language model instances, each with its own context window. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

When to Activate

Triggers

This skill activates on semantic intent, NOT keywords.

Active Signals:

• "Help me think through..."
• "Design a..."
• "Critique my..."
• "What if..."
• "Why did this fail?"

Passive Signals:

• Any request where the solution path is not immediately obvious.
• Any request requiring context beyond a single file.