Generates a breakdown of your token usage and costs across agents and models, with a tier-based view that shows how much Sonnet/Opus spend could have been handled by cheaper boosters. Pulls from the cost-tracking namespace, applies current Claude pricing (Haiku to Opus), and checks your spend against configured budgets. The tier breakdown is the most useful line: it tells you exactly what fraction of your expensive LLM calls were Tier 1 eligible and could have been routed differently. Also integrates benchmark data from latest.json when available to show measured booster performance. Best used daily or weekly to catch runaway costs before they become budget alerts.
npx skills add https://github.com/ruvnet/ruflo --skill cost-report