Dispatch
The harness is a budget line
A local proxy (RTK) shows 4.4M "saved" tokens (45.3%) across 9,892 cumulative commands (global scope). That figure reads like a lower bill; that reading is incomplete. That "saving" only exists because a harness (hooks, gates, routing) produces it and keeps producing it. A deliberate share of my AI budget has to fund that upkeep, not just more generation tokens.
ai-roi inference-cost coding-agents