<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Productivity on David Rothera</title><link>https://davidrothera.me/tags/productivity/</link><description>Recent content in Productivity on David Rothera</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 18 Apr 2026 10:00:00 +0000</lastBuildDate><atom:link href="https://davidrothera.me/tags/productivity/index.xml" rel="self" type="application/rss+xml"/><item><title>Claude Code's New Auto Permission Mode — Fewer Prompts, Smarter Guardrails</title><link>https://davidrothera.me/posts/auto-permission-mode-claude-code-opus-4-7/</link><pubDate>Sat, 18 Apr 2026 10:00:00 +0000</pubDate><guid>https://davidrothera.me/posts/auto-permission-mode-claude-code-opus-4-7/</guid><description>Claude Code&amp;rsquo;s new auto permission mode pairs a background safety classifier with sandboxing and the /fewer-permission-prompts skill for far fewer prompts. Here&amp;rsquo;s how all three fit together.</description></item></channel></rss>