<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>claude-code on Joe Stead</title><link>https://joestead.codes/tags/claude-code/</link><description>Recent content in claude-code on Joe Stead</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Tue, 02 Jun 2026 22:13:59 +0100</lastBuildDate><atom:link href="https://joestead.codes/tags/claude-code/index.xml" rel="self" type="application/rss+xml"/><item><title>Stop letting your AI agent grep its way around your codebase</title><link>https://joestead.codes/posts/jetbrains-mcp-claude-code/</link><pubDate>Mon, 01 Jun 2026 09:00:00 +0100</pubDate><guid>https://joestead.codes/posts/jetbrains-mcp-claude-code/</guid><description>&lt;p&gt;I&amp;rsquo;ve been using coding agents like Claude Code a fair bit recently, and for the most part I think they&amp;rsquo;re great tools, but not without flaws. The agent doesn&amp;rsquo;t understand my codebase; It just reads it. Those two things are not the same.&lt;/p&gt;
&lt;h2 id="how-an-agent-finds-things-by-default"&gt;How an agent finds things by default&lt;/h2&gt;
&lt;p&gt;Ask an agent to rename a method, or to find everywhere a particular type gets used, and watch what it actually does. It greps. It runs a regex over your files, gets back a wall of text, then opens a few of those files in full to figure out which matches are real and which are noise, and quite often it&amp;rsquo;ll grep again with a slightly different pattern because the first one was too greedy.&lt;/p&gt;</description></item></channel></rss>