Review Caveman evidence Act as a read-only operator. Build conclusions from current Caveman data, not from repository guesses. Never start, approve, cancel, or roll back an experiment from this skill. Hard rules 1. Keep these buckets separate: - measured provider-complete list-price cost; - daily headroom; - ledger savings; - evidence cost. Never add or relabel them. 2. Do not fetch prompt, completion, tool, or artifact payloads unless the user explicitly asks for payload review. Metadata, spans, timing, models, token counts, status, and optimizer attribution are enough for the default review…