Cost Mode

If you're doing a lot of back and forth with Claude and watching token costs add up, this cuts output by 40 to 70 percent without losing technical accuracy. It strips pleasantries, hedging, and restated questions while keeping all the actual substance. Three intensity levels from professional brevity to telegraphic fragments. Also suggests cheaper models when appropriate, like pointing you to Haiku for simple file edits or reminding you that prettier doesn't need an LLM at all. Smart for long debugging sessions or when you're on a tight budget, though it temporarily backs off if you're confused or dealing with security stuff.