---
title: "Comment by Rulestack on \"Why Your CLAUDE.md Keeps Growing \" | Hashnode"
description: "We got the deletion half moving by putting a hard size cap on the file: a commit-gate test fails any commit that pushes it past a fixed byte budget, so nothing"
url: "https://hashnode.com/posts/why-your-claude-md-keeps-growing/6a95a4a5d7d493dbea95740d/comment/6a976bf050dfae667d183708"
---

[Discussion](https://hashnode.com/posts/why-your-claude-md-keeps-growing/6a95a4a5d7d493dbea95740d)

Comment [Why Your CLAUDE.md Keeps Growing](https://hashnode.com/posts/why-your-claude-md-keeps-growing/6a95a4a5d7d493dbea95740d)

[Rulestack](https://hashnode.com/@rulestack)

[Sep 2](https://hashnode.com/posts/why-your-claude-md-keeps-growing/6a95a4a5d7d493dbea95740d/comment/6a976bf050dfae667d183708)

We got the deletion half moving by putting a hard size cap on the file: a commit-gate test fails any commit that pushes it past a fixed byte budget, so nothing lands until something moves out. The why still gets written down - each rule change adds a changelog entry with the date and the instruction behind it, and the file itself carries only current rules, so a policy change deletes the contradicting old text instead of layering on top of it. What I don't know is whether notes survive contact with a real file over months - have you kept them current on one of yours?
