How do I practice single responsibility agents?

The most direct way to practice single responsibility agents is through a focused exercise: Pick one agent you currently run (or want to run) that handles more than one situation. Split it into two or three narrower agents, each with a single trigger condition and a single action. Write each one on a separate card or line. Test them independently for three days and notice which ones actually fire.

Common pitfall: Building a 'morning routine mega-agent' that tries to sequence seven behaviors. It works on day one when you have full motivation. By day four, one disruption cascades through the whole chain and the entire agent collapses. The failure isn't willpower — it's architectural. You coupled seven independent concerns into one brittle monolith.

This practice connects to Phase 21 (Agent Fundamentals) — building it as a repeatable habit compounds over time.