Why a growing CLAUDE.md stops working

Every team that runs Claude Code long enough grows a CLAUDE.md. It starts as twelve lines. Six months later it is the onboarding doc, the billing policy, the deploy ritual, and the paragraph someone pasted from a Slack argument in March.

You feel it first as tokens. The file is in the prompt on every call. A line about refund windows is in the context of a CSS change. A line about CSS is in the context of a refund. There is no off switch for a paragraph that no longer applies to this task, because the file has no idea what this task is.

Chroma tested 18 frontier models and watched accuracy fall as the input grew. They called it context rot. A CLAUDE.md that only ever gets longer is a context-rot machine you maintain by hand.

The objection writes itself. If a context file barely helps and costs a fifth more, a context product that pipes more of the same file through a nicer search box should not help either. Dumping is the thing the study measured. Subtraction is the move that is left.

Harbor picks the few facts that fit this task and leaves the rest out. It does not win by stuffing the prompt. Two facts out of hundreds is the claim on the run plate; a growing instruction file is the thing that plate is arguing with.

A file also cannot expire a line. The billing policy from March stays in the prompt until a person deletes it. Harbor flags a rule when it stops being true. That is a different claim from “we retrieve better.”

What a file cannot do at all is tell you which of those lines the agent used. That is served vs cited.