sync: update cli-for-beginners Learning Hub with upstream changes (2026-07-31)

- ch01: clarify plan mode is read-only until user approves
- ch04: add multi-turn subagents tip and new /model plan section
- ch05: update skill list examples to show (disabled) state, add disabled skills tip

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

website/src/content/docs/learning-hub/cli-for-beginners/01-setup-and-first-steps.md

@@ -3,7 +3,7 @@ title: '01 · First Steps'
 description: 'Experience your first GitHub Copilot CLI demos and learn the three main interaction modes.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-17
+lastUpdated: 2026-07-31
 ---
 
 ![Chapter 01: First Steps](/images/learning-hub/copilot-cli-for-beginners/01/chapter-header.png)
@@ -316,7 +316,7 @@ Step 4: Test the flow
 Proceed with implementation? [Y/n]
 ```
 
-**Key insight**: Plan mode lets you review and modify the approach before any code is written. Once a plan is complete, you can even tell Copilot CLI to save it to a file for later reference. For example, "Save this plan to `mark_as_read_plan.md`" would create a markdown file with the plan details.
+**Key insight**: Plan mode lets you review and modify the approach before any code is written. While in plan mode, Copilot CLI is **read-only** and will not edit any files or run commands that change your workspace until you approve and move to implementation. This keeps you safely in the "thinking" stage until you're ready. Once a plan is complete, you can even tell Copilot CLI to save it to a file for later reference. For example, "Save this plan to `mark_as_read_plan.md`" would create a markdown file with the plan details.
 
 > 💡 **Want something more complex?** Try: `/plan Add search and filter capabilities to the book app`. Plan mode scales from simple features to full applications.
 

website/src/content/docs/learning-hub/cli-for-beginners/04-agents-and-custom-instructions.md

@@ -3,7 +3,7 @@ title: '04 · Create Specialized AI Assistants'
 description: 'Mirror the source chapter on custom agents and custom instructions for GitHub Copilot CLI.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-10
+lastUpdated: 2026-07-31
 ---
 
 ![Chapter 04: Agents and Custom Instructions](/images/learning-hub/copilot-cli-for-beginners/04/chapter-header.png)
@@ -104,6 +104,25 @@ What about the Task Agent? It works behind the scenes to manage and track what i
 | ✅ **Success** | Brief summary (e.g., "All 247 tests passed", "Build succeeded") |
 | ❌ **Failure** | Full output with stack traces, compiler errors, and detailed logs |
 
+> 💡 **Multi-turn subagents**: Subagents (background tasks launched by agents) support follow-up messages. While an agent is running in the background, you can open `/tasks` to view it and send follow-up instructions. You don't have to wait for it to finish before guiding it further. Think of it like being able to tap your assistant on the shoulder mid-task to give extra direction.
+
+### Choosing a Model for Plan Mode
+
+By default, `/plan` uses the same AI model you've selected for your session. You can pick a *different* model to use only while in plan mode — great for using a faster or less expensive model for planning, then switching back to a more powerful one for implementation:
+
+```bash
+copilot
+
+# Open the model picker for plan mode only
+> /model plan
+
+# Or specify a model ID directly (use 'off' to clear the plan-mode model)
+> /model plan gpt-5.6-sol
+
+# Leave plan mode and the model reverts to your session model automatically
+```
+
+> 💡 **Why set a plan-mode model?** A high-quality plan created by a frontier model upfront can actually save tokens and time overall. A precise, well-scoped plan means fewer back-and-forth corrections during implementation.
 
 > 📚 **Official Documentation**: [GitHub Copilot CLI Agents](https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-agents)
 

website/src/content/docs/learning-hub/cli-for-beginners/05-skills.md

@@ -3,7 +3,7 @@ title: '05 · Automate Repetitive Tasks'
 description: 'Mirror the source chapter on skills that load automatically for repeated GitHub Copilot CLI workflows.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-03
+lastUpdated: 2026-07-31
 ---
 
 ![Chapter 05: Skills System](/images/learning-hub/copilot-cli-for-beginners/05/chapter-header.png)
@@ -527,10 +527,10 @@ Once you're in an interactive Copilot session, use `/skills` (or its shortcut `/
 # From the terminal (no interactive session needed):
 copilot skill list
 
-Available skills:
+Project skills:
 - security-audit: Security-focused code review checking OWASP Top 10
 - generate-tests: Generate comprehensive unit tests with edge cases
-- code-checklist: Team code quality checklist
+- code-checklist: Team code quality checklist (disabled)
 ...
 
 # Or from inside a Copilot session:
@@ -538,10 +538,10 @@ copilot
 
 > /skills list
 
-Available skills:
+Project skills:
 - security-audit: Security-focused code review checking OWASP Top 10
 - generate-tests: Generate comprehensive unit tests with edge cases
-- code-checklist: Team code quality checklist
+- code-checklist: Team code quality checklist (disabled)
 ...
 
 > /skills info security-audit
@@ -552,6 +552,8 @@ Location: .github/skills/security-audit/SKILL.md
 Description: Security-focused code review checking OWASP Top 10 vulnerabilities
 ```
 
+> 💡 **Disabled skills**: Skills marked as `(disabled)` are installed but not currently active. They won't be triggered by prompts until re-enabled. This can happen if a skill's `SKILL.md` file has a configuration issue, or if the skill was explicitly disabled. You can enable/disable skills by running `/skills`.
+
 ---
 
 <details>