<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Documentation on mhbxyz.me</title><link>https://mhbxyz.github.io/en/tags/documentation/</link><description>Recent content in Documentation on mhbxyz.me</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 03 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://mhbxyz.github.io/en/tags/documentation/index.xml" rel="self" type="application/rss+xml"/><item><title>Make a repository usable by a development agent</title><link>https://mhbxyz.github.io/en/articles/agentic-engineering-wiki-make-a-repository-usable-by-an-agent/</link><pubDate>Thu, 03 Sep 2026 00:00:00 +0000</pubDate><guid>https://mhbxyz.github.io/en/articles/agentic-engineering-wiki-make-a-repository-usable-by-an-agent/</guid><description>&lt;h2 id="the-repository-should-explain-how-to-work"&gt;The repository should explain how to work&lt;/h2&gt;
&lt;p&gt;An agent can read code, but that does not tell it which command runs the tests, which migrations are sensitive, or what counts as finished work. A human joining the project asks the same questions. In &lt;a href="https://github.com/mhbxyz/agentic-engineering-wiki"&gt;Agentic Engineering Wiki&lt;/a&gt;, I collected a way to make those answers visible in the repository.&lt;/p&gt;
&lt;p&gt;The starting point is modest: a short &lt;code&gt;AGENTS.md&lt;/code&gt; and stable project commands. The first states the constraints; the second makes them verifiable. Adding integrations before these basics mainly creates more ways to make a mistake.&lt;/p&gt;</description></item></channel></rss>