<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Prompt on StackOnward</title><link>https://stackonward.com/tags/prompt/</link><description>Recent content in Prompt on StackOnward</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Fri, 11 Sep 2026 04:30:00 +0800</lastBuildDate><atom:link href="https://stackonward.com/tags/prompt/index.xml" rel="self" type="application/rss+xml"/><item><title>How to Write Claude Code Prompts: Current Task Only</title><link>https://stackonward.com/posts/coding-agent-task-prompt/</link><pubDate>Fri, 11 Sep 2026 04:10:00 +0800</pubDate><guid>https://stackonward.com/posts/coding-agent-task-prompt/</guid><description>&lt;p&gt;How to write Claude Code prompts depends on what this task still lacks after project configuration. Project rules already hold the repo map, commands, and long-lived boundaries. Skills already hold repeatable workflows. Hooks and CI run deterministic actions. Permission policy limits tools. The current prompt only needs the state to change, the evidence you already have, the affected range, the authorization boundary, and the result that must appear when the work is done.&lt;/p&gt;
&lt;p&gt;The prompt does not need YAML, XML, or a fixed form. A local defect can be short. Context that crosses several owners is added only when that context changes the result. The test is not word count or field count. It is whether the agent can start from the current project, make the change inside authorization, and confirm the software reached the target state.&lt;/p&gt;</description></item></channel></rss>