Our project CLAUDE.md crossed 4,000 tokens last quarter, and the agent started missing rules it had been respecting for months. Not the rules at the top. The rules in the middle. The ones buried under three other sections of guidance, the ones the agent could reach if it stayed focused but did not reach reliably when it was deep in a task.
The story would have ended with "make the file shorter" except for the part where most of those rules had earned their place. Each one had an incident behind it. Each one had a reviewer who would defend it. The harness was not bloated; the harness was honest. And the agent was still missing rules.
The conclusion that took me too long to reach: the harness has a token budget, and we had blown it.
The cost nobody puts on a P&L
Every CLAUDE.md line costs context. The agent reads the harness on every session, in every window, before any of your task-specific context arrives. A 4,000-token CLAUDE.md is 4,000 tokens the agent is not using for the file you actually asked it to edit.
