What problem does it solve? Token-saving prompt modes often claim savings without evidence, leaving users unable to tell whether the mode actually helped or cost more than it saved. This Skill reads the real session log and reports measured input/output tokens, estimated savings, rule overhead, and net impact. ## Core Features & Use Cases - Real token receipts: Reads the JSONL session log on disk directly, so numbers come from recorded usage rather than model estimation. - Net savings accounting: Computes estimated rule overhead (default 1,250 input tokens per turn, configurable via CAVEMAN_RULE_OVERHEAD_TOKENS) and subtracts it from gross savings, flagging net-negative sessions plainly. - Statusline badge support: Writes a lifetime-savings suffix file consumed by the statusline badge for a glanceable gross-savings summary. - Use Case: After a long coding session in caveman mode, run /caveman-stats to see whether the output-token savings actually exceeded the input-token cost of the injected rules for that workload. ## Quick Start Type /caveman-stats in the session to display the current session's measured token usage, estimated savings, rule overhead, and net result.
