Token efficiency

Reduce repetition, not verification. Context size, cached input, output and reasoning usage are different measurements; fewer bytes are not proof of a lower bill or unchanged answer quality.

Where usage actually goes

Measured from one heavy user's local logs (2026-10-10, ~1,100 sessions across Codex, Claude Code, Hermes and Grok). Run python TOOLS/usage_report.py for your own numbers before changing anything.