<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CLAUDE.md on Devops Monk</title><link>https://devops-monk.com/tags/claude.md/</link><description>Recent content in CLAUDE.md on Devops Monk</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 26 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://devops-monk.com/tags/claude.md/index.xml" rel="self" type="application/rss+xml"/><item><title>Writing a CLAUDE.md That Actually Works</title><link>https://devops-monk.com/2026/04/writing-claude-md-that-works/</link><pubDate>Sun, 26 Apr 2026 00:00:00 +0000</pubDate><guid>https://devops-monk.com/2026/04/writing-claude-md-that-works/</guid><description>Every CLAUDE.md file gets loaded into context on every session. Most teams treat it like documentation — a place to describe the project, list the tech stack, explain what the tests do. That is the wrong mental model and it is why most CLAUDE.md files are both too long and too ineffective.
CLAUDE.md is behavioral programming. Its job is to change how Claude makes decisions, not to describe facts that Claude can read from the codebase itself.</description></item></channel></rss>