Skills Productivity Display Real Token Usage And Savings

Display Real Token Usage And Savings

v20260803
caveman-stats
Provides real-time, non-AI estimated statistics on token consumption and potential cost savings for the current session. This skill reads directly from the session log, offering transparent metrics like rule overhead and net savings, allowing users to accurately gauge efficiency and cost impact of complex AI operations.
Get Skill
53 downloads
Overview

This skill is delivered by hooks/caveman-stats.js (read by hooks/caveman-mode-tracker.js on /caveman-stats). The model does not need to do anything when this skill fires — the hook returns decision: "block" with the formatted stats as the reason. The user sees the numbers immediately.

Output also includes Est. rule overhead and Est. net lines wherever a savings estimate exists with a known turn count. Rule overhead is the estimated per-turn INPUT-token cost of the injected caveman rules (default 1,250 tokens/turn, override with CAVEMAN_RULE_OVERHEAD_TOKENS) times the turn count. Net is savings minus that overhead — when negative, the output says so plainly and suggests turning caveman off for that workload, rather than hiding the net-negative regime behind a gross-savings number (see docs/HONEST-NUMBERS.md).

Info
Category Productivity
Name caveman-stats
Version v20260803
Size 1.13KB
Updated At 2026-08-04
Language