Session Compare

When you need to understand why one Claude Code session burned through tokens while another sailed through efficiently, this pulls side-by-side comparisons from Agent Monitor data. You can compare specific session IDs, pit your best against worst performers, or benchmark one session against your rolling average. It breaks down token usage by type (input, output, cache reads and writes), shows cost differences with the pricing engine, maps out tool usage patterns, and traces where sessions diverged in their event timelines. The "Lessons Learned" section is the real payoff, translating raw metrics into actual takeaways about agent strategies and tool choice. Most useful during post-mortems or when you're trying to figure out why similar tasks sometimes cost 5x more than they should.