I open-sourced a privacy-safe benchmark for coding-agent token experiments

Overview

“Total tokens” is often treated as real consumption, even though cached input, fresh input, and output have very different costs. I built agent-token-bench , a free MIT-licensed CLI that analyzes local Codex rollout files and emits numeric metrics only—never prompts, responses, reasoning content, tool arguments/results, or workspace paths. It measures: Cached versus uncached input Output and reasoning-output totals Credit-equivalent usage using a dated rate card Tool calls, polling, and compacti

SpinGraph analysis pending — check back after processing.