docs: update Learning Hub with recent Copilot CLI features (v1.0.23-v1.0.30) (#1421)

- copilot-configuration-basics.md: Add /ask, /env, /statusline commands
  and --mode/--autopilot/--plan startup flags
- automating-with-hooks.md: Document preToolUse modifiedArgs/updatedInput
  and additionalContext fields for modifying tool arguments
- understanding-mcp-servers.md: Add /mcp install registry section and
  note that type field is optional for remote MCP servers
- installing-and-using-plugins.md: Add copilot plugin marketplace update
  command and deprecation notice for repo/URL/path installs
- using-copilot-coding-agent.md: Add Remote Control section
  (replaces steering feature)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
2026-04-20 12:32:57 +10:00
committed by GitHub
parent b360c76848
commit d7cf720ede
5 changed files with 130 additions and 5 deletions

View File

@@ -3,7 +3,7 @@ title: 'Using the Copilot Coding Agent'
description: 'Learn how to use GitHub Copilot coding agent to autonomously work on issues, generate pull requests, and automate development tasks.'
authors:
- GitHub Copilot Learning Hub Team
lastUpdated: 2026-03-25
lastUpdated: 2026-04-16
estimatedReadingTime: '12 minutes'
tags:
- coding-agent
@@ -334,6 +334,45 @@ This repository provides a curated collection of agents, skills, and hooks desig
> **Example workflow**: Combine a `test-specialist` agent with a `database-migrations` skill and a linting hook. Assign an issue to the coding agent using the test-specialist agent — it will automatically pick up the migrations skill when relevant, and the hook ensures all code is formatted before completion.
## Remote Control
You can connect to and steer a running coding agent session from a local Copilot CLI terminal using **remote control**. This lets you observe the agent's progress, send follow-up prompts, and redirect its work in real time — without waiting for it to open a PR first.
### Starting a Remote-Controlled Session
Launch a session that registers with GitHub for remote access:
```bash
copilot --remote
```
Or open a remote control tab from inside an existing session:
```
/remote
```
The **Remote** tab in the CLI shows all active coding agent tasks from the repository. Select a task to connect and begin sending steering messages.
### Resuming from the Session Picker
Remote sessions also appear in the `--resume` picker, so you can reconnect to a coding agent session you were previously controlling without needing to know the session ID:
```bash
copilot --resume
```
### Why Use Remote Control?
| Scenario | Benefit |
|----------|---------|
| Long-running tasks | Monitor progress without waiting for the final PR |
| Mid-course corrections | Redirect the agent if it heads in the wrong direction |
| Interactive refinement | Provide clarification and feedback as the agent works |
| No PR required | You can steer tasks that haven't yet opened a pull request |
> **Note**: Remote control replaces the earlier "steering" feature. If you see references to steering in older documentation, remote control is the updated equivalent.
## Hooks and the Coding Agent
Hooks are especially valuable with the coding agent because they provide deterministic guardrails for autonomous work: