<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Developer-Tools on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/developer-tools/</link><description>Recent content in Developer-Tools on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 02 Jun 2026 08:00:00 +0000</lastBuildDate><atom:link href="https://renezander.com/tags/developer-tools/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Code Stops Following Your CLAUDE.md: Read-Once Rules and Hooks</title><link>https://renezander.com/blog/claude-md-rules-hooks/</link><pubDate>Tue, 02 Jun 2026 08:00:00 +0000</pubDate><guid>https://renezander.com/blog/claude-md-rules-hooks/</guid><description>&lt;p>Some of the rules in your CLAUDE.md should not be rules at all.&lt;/p>
&lt;p>Not because they are wrong. Because you have written the things you cannot afford to lose into a file the model reads once and then slowly forgets. A preference survives that. A constraint does not.&lt;/p>
&lt;p>A month ago I posted ten CLAUDE.md rules. The most common reply was not &amp;ldquo;add an eleventh.&amp;rdquo; It was quieter than that: the rules stop getting followed. Forty thousand tokens into a session, the model edits the file you told it never to touch, or commits straight to main after you wrote, in bold, that it never should. Maybe half of what is in my own file is decoration. The half that is not decoration is the half that scares me.&lt;/p></description></item></channel></rss>