Benchmark

Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens, tool count, and workflow complexity score — and report where each metric lands as a percentile of the population. Tells you whether a session was normal, cheap, or an outlier. Use when judging whether a session was typical or out of band.

hoangsonww Updated 1.2k repo stars

File contents

hoangsonww/Claude-Code-Agent-Monitor commit f7a6cdbef6

Frequently asked questions

npx get-skill add hoangsonww/benchmark