claude-performance
ClaudePlugin
Weekly performance digest for Claude Code. Reads JSONL session data, computes six effectiveness metrics (activity mix, one-shot edit rate, subagent turn count, model mix, project allocation, hookify firings), fires diagnostic rules, and writes behavioral rules into CLAUDE.md so future sessions adapt. Measurement layer for self-improving AI workflows.
Best rank—Not in a ranked chart
Charts—
LaunchedApr 28