<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>dsh-vision-subagent — release evidence</title>
  <id>https://deeplugin.store/plugins/deeplugin-8c2864a50158a88324e0.atom.xml</id>
  <updated>2026-08-17T04:59:26Z</updated>
  <link rel="self" type="application/atom+xml" href="https://deeplugin.store/plugins/deeplugin-8c2864a50158a88324e0.atom.xml"/>
  <link rel="alternate" href="https://deeplugin.store/plugins/deeplugin-8c2864a50158a88324e0.html"/>
  <entry>
    <title>New: dsh-vision-subagent</title>
    <id>tag:deeplugin.store,2026-08-17:deeplugin-8c2864a50158a88324e0/4e8024ade33c4b17</id>
    <updated>2026-08-17T04:59:26Z</updated>
    <link rel="alternate" href="https://deeplugin.store/plugins/deeplugin-8c2864a50158a88324e0.html"/>
    <author><name>ruby1304</name></author>
    <category term="vision"/>
    <summary>Vision for text-only agents: a vision_agent tool that delegates image reading to a one-shot subagent on a configurable vision route (MiniMax/Kimi), plus a Codex-style paste bridge — images are analyzed on an isolated context and only text reaches the main session. Exact install spec: dsh-vision-subagent. Source event: awesome-dsh-plugin/awesome-dsh-plugin; changed: listed.</summary>
  </entry>
</feed>
