docs: update learning hub for Copilot CLI v1.0.72–v1.0.75 changes

- automating-with-hooks: document agentStop loop prevention and stop_hook_active flag (v1.0.72)
- building-custom-agents: document relative link resolution in agent instructions (v1.0.73)
- copilot-configuration-basics: add /model --plan for plan-mode model selection (v1.0.74)
- installing-and-using-plugins: document Open Plugin Spec v1 and mcp.json support (v1.0.74)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

website/src/content/docs/learning-hub/automating-with-hooks.md

@@ -3,10 +3,7 @@ title: 'Automating with Hooks'
 description: 'Learn how to use hooks to automate lifecycle events like formatting, linting, and governance checks during Copilot agent sessions.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-13
-estimatedReadingTime: '8 minutes'
-tags:
-  - hooks
+lastUpdated: 2026-07-27
   - automation
   - fundamentals
 relatedArticles:
@@ -369,6 +366,19 @@ Run ESLint after the agent finishes responding and block if there are errors:
 
 If the lint command exits with a non-zero status, the action is blocked.
 
+> **agentStop loop prevention (v1.0.72+)**: If an `agentStop` hook *always* exits with a non-zero code, prior versions would loop indefinitely as the CLI retried. Since v1.0.72, the CLI ends the turn after **8 consecutive blocks** to prevent runaway loops. Additionally, `agentStop` hooks now receive a `stop_hook_active` flag in their JSON input so they can detect a forced continuation and self-limit. Use this flag to short-circuit your hook when it detects it's been invoked repeatedly in the same turn:
+>
+> ```bash
+> #!/usr/bin/env bash
+> INPUT=$(cat)
+> # If we've already blocked multiple times, let the turn proceed
+> if echo "$INPUT" | jq -e '.stop_hook_active == true' > /dev/null 2>&1; then
+>   exit 0
+> fi
+> # Normal lint check
+> npx eslint . --max-warnings 0
+> ```
+
 ### Security Gating with preToolUse
 
 Block dangerous commands before they execute. Use the `matcher` field to target only the `bash` tool, so the hook doesn't fire for file edits or other tools:

website/src/content/docs/learning-hub/building-custom-agents.md

@@ -3,11 +3,7 @@ title: 'Building Custom Agents'
 description: 'Learn how to create specialized GitHub Copilot agents with custom personas, tool integrations, and domain expertise.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-09
-estimatedReadingTime: '10 minutes'
-tags:
-  - agents
-  - customization
+lastUpdated: 2026-07-27
   - fundamentals
 relatedArticles:
   - ./what-are-agents-skills-instructions.md
@@ -101,6 +97,8 @@ For MCP server tools, reference them by server name (e.g., `postgres`, `docker`)
 
 After the frontmatter, write Markdown instructions that define the agent's behavior. Structure these clearly:
 
+> **Relative links in instructions (v1.0.73+)**: Links in your agent's Markdown instructions (e.g., `[style guide](./docs/style.md)`) are now resolved **relative to the agent file's location**, not the repository root. This means you can reference files that live alongside your agent in `.github/agents/` without worrying about path conflicts. For example, if your agent is at `.github/agents/api-reviewer.agent.md`, a link to `[conventions](./api-conventions.md)` resolves to `.github/agents/api-conventions.md`.
+
 ````markdown
 ---
 name: 'API Design Reviewer'

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

@@ -3,10 +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
-estimatedReadingTime: '10 minutes'
-tags:
-  - configuration
+lastUpdated: 2026-07-27
   - setup
   - fundamentals
 relatedArticles:
@@ -468,6 +465,16 @@ The settings dialog supports search — type to filter settings by name. Changes
 /model --local      # view/edit your personal model preference
 ```
 
+*(v1.0.74+)* Use `/model plan` (or `/model --plan`) to set a **plan-mode–specific model**. This lets you use a lighter, faster model while planning and a more capable model when executing:
+
+```
+/model --plan                   # open the model picker scoped to plan mode
+/model --plan claude-haiku-4-5  # set a specific model for plan mode
+/model --plan off               # clear the plan-mode model (reverts to session model)
+```
+
+The plan-mode model reverts to your session model automatically when you leave plan mode.
+
 These flags mirror the **Repo** and **Repo (local)** scope tabs available in the `/settings` dashboard (v1.0.71+), making it easier to manage per-repository vs. user-global configuration without ambiguity. In v1.0.71+, the `/settings` dashboard also shows **Repo** and **Repo (local)** tabs alongside the existing user-level view, giving you a unified place to see which settings are applied at each layer.
 
 GitHub Copilot CLI has two commands for managing session state, with distinct behaviours:

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

@@ -3,10 +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
-estimatedReadingTime: '8 minutes'
-tags:
-  - plugins
+lastUpdated: 2026-07-27
   - copilot-cli
   - fundamentals
 relatedArticles:
@@ -31,7 +28,7 @@ A plugin bundles one or more of the following components:
 | **Custom Agents** | Specialized AI assistants with tailored expertise | `agents/*.agent.md` |
 | **Skills** | Discrete callable capabilities with bundled resources | `skills/*/SKILL.md` |
 | **Hooks** | Event handlers that intercept agent behavior | `hooks.json` or `hooks/` |
-| **MCP Servers** | Model Context Protocol integrations for external tools | `.mcp.json` or `.github/mcp.json` |
+| **MCP Servers** | Model Context Protocol integrations for external tools | `.mcp.json`, `.github/mcp.json`, or Open Plugin Spec `mcp.json` (v1.0.74+) |
 | **LSP Servers** | Language Server Protocol integrations | `lsp.json` or `.github/lsp.json` |
 | **Extensions** | IDE extensions installable via the plugin marketplace (v1.0.62+) | `extensions/` |
 
@@ -200,6 +197,8 @@ Or from an interactive session:
 
 > **Deprecation notice**: Installing plugins directly from a GitHub repository URL, raw URL, or local file path (e.g., `copilot plugin install github/awesome-copilot`) is deprecated and will be removed in a future release. Use marketplace-based installation instead.
 
+> **Open Plugin Spec v1 and `mcp.json` (v1.0.74+)**: Copilot CLI now supports the **Open Plugin Spec v1** manifest format in addition to the proprietary `plugin.json` format. This means plugins authored in `mcp.json` configuration format (used by tools like Claude Code) are automatically recognized and installable. If your team uses a shared `mcp.json` for MCP server configuration, it can also serve as a plugin manifest — no conversion needed.
+
 ### From VS Code
 
 Browse to the plugin via `@agentPlugins` in the Extensions search view or via **Chat: Plugins** in the Command Palette, then click **Install**.