<?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>AGENTS.md on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/agents.md/</link><description>Recent content in AGENTS.md on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Thu, 05 Nov 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/agents.md/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Native Digest 2026-11-05</title><link>https://douyixuan.github.io/posts/ai-native/2026-11-05/</link><pubDate>Thu, 05 Nov 2026 08:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-native/2026-11-05/</guid><description>两篇 11 月 3 日提交的原创软件工程研究，从 Agent Context File 的指令措辞与 GitHub Skills 的长期演化出发，揭示代理遵循约束和维护可复用能力时的可靠性缺口，并讨论可执行的回归验收。</description></item></channel></rss>