Session Report

When you need to understand what actually happened in a Claude Code session, this pulls everything from the Agent Monitor API and formats it into a readable report. You get per-model token breakdowns including cache read/write stats, exact costs via matched pricing rules, the full agent hierarchy with subagent types, tool invocation counts, compaction events, and a timeline of errors and turn durations. It's built for the localhost:4820 monitor setup, so you can review a specific session ID, grab the latest one, or summarize a date range. The cache hit rate calculation and baseline token tracking are especially useful for spotting context management issues before your bill gets weird.