[bot] Update Learning Hub: Claude Opus 5, gemini-3.6-flash, /model plan, and Open Plugin Spec v1

website/src/content/docs/learning-hub/copilot-configuration-basics.md

@@ -3,7 +3,7 @@ title: 'Copilot Configuration Basics'
 description: 'Learn how to configure GitHub Copilot at user, workspace, and repository levels to optimize your AI-assisted development experience.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-13
+lastUpdated: 2026-07-24
 estimatedReadingTime: '10 minutes'
 tags:
   - configuration
@@ -449,6 +449,25 @@ The model picker opens in a **full-screen view** with inline reasoning effort ad
 
 **Model family aliases** (v1.0.64+): Instead of typing a full model name, you can use short family aliases in the model setting: `opus`, `sonnet`, `haiku` (Anthropic), and `gpt`, `gemini` (Google/OpenAI). The CLI resolves the alias to the latest available model in that family. This is especially useful in scripts or configuration files where you want to track the best model in a family without hardcoding a version string.
 
+**New models** (v1.0.74–v1.0.75): GitHub Copilot CLI now supports **Claude Opus 5** (Anthropic's most capable model) and **gemini-3.6-flash** (a fast, lightweight Gemini model from Google). You can select these from the model picker or specify them directly:
+
+```
+/model claude-opus-5
+/model gemini-3.6-flash
+```
+
+Both are also reachable via the `opus` and `gemini` family aliases.
+
+**Plan mode model selection** *(v1.0.74+)*: You can now set a separate model specifically for plan mode using `/model plan` (or `/model --plan`). This lets you use a cheaper or faster model for planning while keeping a more capable model for execution:
+
+```
+/model plan claude-haiku-4   # use a fast model while in plan mode
+/model plan off              # clear the plan-mode model override (revert to session model)
+/model plan                  # open the picker to choose interactively
+```
+
+When you leave plan mode the session reverts to your regular session model automatically. Plan mode also now permits writing planning artifacts to the session folder (e.g., `plan.md` in `~/.copilot/session-state/`) while continuing to block file mutations outside that scope.
+
 ### CLI Session Commands
 
 The `/settings` command (v1.0.61+) opens an interactive dialog to browse and edit all user settings in one place. Use it to discover available settings, toggle options, and update values without manually editing your config file:

website/src/content/docs/learning-hub/installing-and-using-plugins.md

@@ -3,7 +3,7 @@ title: 'Installing and Using Plugins'
 description: 'Learn how to find, install, and manage plugins that extend GitHub Copilot CLI with reusable agents, skills, hooks, and integrations.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-13
+lastUpdated: 2026-07-24
 estimatedReadingTime: '8 minutes'
 tags:
   - plugins
@@ -74,6 +74,26 @@ The `plugin.json` manifest declares what the plugin contains:
 }
 ```
 
+### Open Plugin Spec v1 and mcp.json *(v1.0.74+)*
+
+GitHub Copilot CLI now supports **Open Plugin Spec v1** plugin manifests in addition to the native `plugin.json` format. This means plugins authored for other AI tools that conform to the Open Plugin Spec can be installed directly in Copilot CLI without any conversion.
+
+In addition, the CLI now recognises **`mcp.json`** as a standard configuration file for MCP server definitions. You can place an `mcp.json` alongside your plugin's `plugin.json` to declare MCP server configurations that will be loaded when the plugin is installed:
+
+```json
+// mcp.json
+{
+  "mcpServers": {
+    "my-service": {
+      "command": "npx",
+      "args": ["-y", "my-mcp-server"]
+    }
+  }
+}
+```
+
+This improves interoperability with the broader MCP ecosystem and makes it easier to adopt plugins created by the community or third-party vendors.
+
 ## Why Use Plugins?
 
 You might wonder: why not just copy agent files into your project manually? Plugins provide several advantages: