<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Coding on StackOnward</title><link>https://stackonward.com/tags/ai-coding/</link><description>Recent content in AI Coding on StackOnward</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 11 Sep 2026 04:55:00 +0800</lastBuildDate><atom:link href="https://stackonward.com/tags/ai-coding/index.xml" rel="self" type="application/rss+xml"/><item><title>How to Use Claude Code Hooks: Deterministic Checks</title><link>https://stackonward.com/posts/claude-code-codex-hooks/</link><pubDate>Fri, 11 Sep 2026 04:48:00 +0800</pubDate><guid>https://stackonward.com/posts/claude-code-codex-hooks/</guid><description>&lt;p&gt;How to use Claude Code hooks is not about memorizing every event. It is about whether the action has a clear trigger and a unique result. A project config check belongs in a hook: after the file is written, run the same command. Valid config exits success. Invalid config returns a determined error. The model does not choose the standard.&lt;/p&gt;
&lt;p&gt;Project rules name the config path and the fixed command. The prompt describes this change. A skill handles live judgment. The hook only calls the project command on a matching event. Claude Code and Codex keep their own event config and share the same check.&lt;/p&gt;</description></item></channel></rss>