<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent-Brief on Unbound Force</title><link>https://unboundforce.dev/tags/agent-brief/</link><description>Recent content in Agent-Brief on Unbound Force</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright (c) 2025-2026 Unbound Force</copyright><lastBuildDate>Sun, 03 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://unboundforce.dev/tags/agent-brief/index.xml" rel="self" type="application/rss+xml"/><item><title>Your AI Agent's First Read — Why AGENTS.md Quality Determines Code Quality</title><link>https://unboundforce.dev/blog/agents-md-quality/</link><pubDate>Sun, 03 May 2026 00:00:00 +0000</pubDate><guid>https://unboundforce.dev/blog/agents-md-quality/</guid><description>&lt;h2 id="the-problem"&gt;The Problem&lt;/h2&gt;
&lt;p&gt;Every AI coding agent — Claude Code, Cursor, OpenCode, Copilot — reads a context file at the start of each session. That file tells the agent how to build the project, what conventions to follow, where the tests live, and what constraints to respect. In the Unbound Force ecosystem, this file is &lt;code&gt;AGENTS.md&lt;/code&gt;. Other tools use &lt;code&gt;.cursorrules&lt;/code&gt;, &lt;code&gt;CLAUDE.md&lt;/code&gt;, or similar formats. The name varies; the problem is universal.&lt;/p&gt;</description></item></channel></rss>