[bot] Add /model --session, /model plan, and copilot plugins install --skill documentation

01-setup-and-first-steps/README.md

@@ -513,6 +513,8 @@ copilot
 
 > 💡 **Model family shortcuts**: You can also type a short family alias — like `opus`, `sonnet`, `haiku`, `gpt`, or `gemini` — directly in the `/model` picker instead of scrolling through the full list. Copilot will pick the best available model in that family for you.
 
+> 💡 **Session-only model change**: Use `/model --session` (or `/model -s`) to change the model for just your current session, without changing your global default. This is handy when you want to try a different model for one task without affecting all your future sessions. When the session ends, the model reverts to your usual default.
+
 </details>
 
 ---

04-agents-custom-instructions/README.md

@@ -109,6 +109,24 @@ What about the Task Agent? It works behind the scenes to manage and track what i
 
 > 💡 **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 claude-haiku-4.5
+
+# Leave plan mode and the model reverts to your session model automatically
+```
+
+> 💡 **Why set a plan-mode model?** Planning prompts tend to be lighter tasks — outlining steps, identifying files to change, or scoping work. A faster, cheaper model (like `haiku`) is often plenty for this. Saving your premium-quota model for the actual implementation step is a smart habit.
+
 > 📚 **Official Documentation**: [GitHub Copilot CLI Agents](https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-agents)
 
 ---

05-skills/README.md

@@ -622,9 +622,26 @@ Pre-made skills are also available from community repositories:
 
 - **[Awesome Copilot](https://github.com/github/awesome-copilot)** - Official GitHub Copilot resources including skills documentation and examples
 
+### Installing a Skill with `copilot plugins install`
+
+You can install a skill directly from the Copilot CLI without leaving your terminal. This is the simplest option because it doesn't require any additional tools:
+
+```bash
+# Install a skill from a local file
+copilot plugins install --skill .github/skills/my-skill/SKILL.md
+
+# Install a skill from a URL
+copilot plugins install --skill https://example.com/skills/security-audit/SKILL.md
+
+# Install into the current project (shared with the team via git)
+copilot plugins install --skill https://example.com/skills/my-skill/SKILL.md --scope project
+```
+
+> 💡 **`--scope project` vs default**: By default, skills are installed at the user level (`~/.copilot/skills/`) and are available in all your projects. Adding `--scope project` installs the skill into `.github/skills/` in the current repository, making it part of the project and visible to everyone on your team.
+
 ### Installing a Community Skill with GitHub CLI
 
-The easiest way to install a skill from a GitHub repository is using the `gh skill install` command (requires [GitHub CLI v2.90.0+](https://github.blog/changelog/2026-04-16-manage-agent-skills-with-github-cli/)):
+Another option is the `gh skill install` command (requires [GitHub CLI v2.90.0+](https://github.blog/changelog/2026-04-16-manage-agent-skills-with-github-cli/)):
 
 ```bash
 # Browse and interactively select a skill from awesome-copilot