Merge quattro into plugin auth boundary

manual/17-ai.md

@@ -14,6 +14,7 @@ Omarchy treats AI coding agents as first-class citizens, but it doesn't pick a f
 | `pi`       | [Mario Zechner's Pi](https://github.com/badlogic/pi-mono)        |
 | `omp`      | [Oh My Pi](https://github.com/can1357/oh-my-pi)                  |
 | `ori`      | [Ori](https://openrouter.ai/docs/guides/ori/harness), OpenRouter's harness |
+| `hermes`   | [Hermes](https://hermes-agent.nousresearch.com/), Nous Research's agent  |
 
 `ori` is the odd one out: it runs the other harnesses against OpenRouter's whole model catalog, so `ori claude`, `ori codex`, or `ori opencode` start those agents on whichever model you point them at, and `ori code` is Ori's own agent.
 
@@ -43,7 +44,9 @@ Crashes can also be silenced one program at a time, which is what the diagnosis
 
 ### Desktop apps
 
-The _Install > AI_ menu also carries a couple of graphical AI apps: the ChatGPT desktop app, and Grok Bot for chatting with xAI's models.
+The _Install > AI_ menu also carries a few graphical AI apps: the ChatGPT desktop app, Grok Bot for chatting with xAI's models, and Hermes Desktop.
+
+Hermes Desktop is the one to know about, because there is only ever one Hermes on a machine. The app only runs against a runtime built from its own commit, so it installs one of its own under `~/.hermes` on first launch, which takes a few minutes and shows its own progress. From then on that is the Hermes the terminal `hermes` command and the default agent use too, whichever order you installed them in. Removing the app under _Remove > AI_ takes that runtime with it, and keeps your chats, memories, and the skills Hermes wrote for itself.
 
 ### Local LLMs
 
@@ -51,6 +54,6 @@ Omarchy recommends two ways of running local LLM models: LM Studio and Ollama. L
 
 ### The Omarchy Skill
 
-Agent skills help AI use specific tools in a specific way, and Omarchy ships with a default skill for tailoring the system. Like tweaking your Hyprland config, adjusting the bar, or even creating a new theme from scratch. It's symlinked into the skill directories for Claude Code (`~/.claude/skills`), Codex (`~/.codex/skills`), Pi (`~/.pi/agent/skills`), Antigravity (`~/.gemini/config/skills`), and the generic `~/.agents/skills` location, so most harnesses pick it up automatically.
+Agent skills help AI use specific tools in a specific way, and Omarchy ships with a default skill for tailoring the system. Like tweaking your Hyprland config, adjusting the bar, or even creating a new theme from scratch. It's symlinked into the skill directories for Claude Code (`~/.claude/skills`), Codex (`~/.codex/skills`), Pi (`~/.pi/agent/skills`), Antigravity (`~/.gemini/config/skills`), Hermes (`~/.hermes/skills` and each `~/.hermes/profiles/*/skills`), and the generic `~/.agents/skills` location, so most harnesses pick it up automatically.
 
 But you should treat this skill as experimental. Different models will use it to different effect. It's best to run in plan mode first, so you have an idea of what the agent would like to change. And then be ready to rollback changes or even invoking `omarchy reinstall configs`, if the agent makes a mess of everything.