<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Luce Agentic Notes</title><description>Occasional long-reads on AI workflows that actually ship. No hype.</description><link>https://www.luceagentic.com/</link><language>en-US</language><item><title>Breaking Big Tasks into Claude Code Subagents: A Workflow That Actually Ships</title><link>https://www.luceagentic.com/en/notes/claude-code-subagents-guide/</link><guid isPermaLink="true">https://www.luceagentic.com/en/notes/claude-code-subagents-guide/</guid><description>Claude Code subagents let your main agent delegate independent work to fresh Claude instances — and only receive the conclusion. Here&apos;s when to use them, how to scope tasks that don&apos;t come back shallow, and how to keep your main context from filling up mid-session.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>