<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Cli-Design on Omar Crosby</title>
    <link>https://omarcrosby.com/tags/cli-design/</link>
    <description>Recent content in Cli-Design on Omar Crosby</description>
    <image>
      <title>Omar Crosby</title>
      <url>https://omarcrosby.com/images/og.jpg</url>
      <link>https://omarcrosby.com/images/og.jpg</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 30 Jul 2026 05:48:22 -0400</lastBuildDate>
    <atom:link href="https://omarcrosby.com/tags/cli-design/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>What makes a CLI Claude-friendly</title>
      <link>https://omarcrosby.com/posts/what-makes-a-cli-claude-friendly/</link>
      <pubDate>Thu, 30 Jul 2026 05:48:22 -0400</pubDate>
      <guid>https://omarcrosby.com/posts/what-makes-a-cli-claude-friendly/</guid>
      <description>A concrete look at what turns a command-line tool into something an AI coding agent can drive reliably, with contrived before/after examples for structured output, subcommands, non-interactive defaults, exit codes, self-documenting help, idempotency, and when a token-oriented format like TOON is worth adding as a second output mode.</description>
    </item>
  </channel>
</rss>
