Claude Code Token Usage Hides in History and Tools

Claude Code token usage does go down if you use fewer words. Just not by much in most real sessions. Anthropic’s docs say Claude Code counts far than the line you just typed: system prompt, tool definitions, conversation history, tool inputs, tool outputs, and project memory like CLAUDE.md. That means the folk theory - “write like a caveman and save a ton of tokens” - gets the mechanism backwards. Prompt brevity is a small lever. Session baggage is the big one. A token is a chunk of text the model reads or writes.