Document recent Copilot CLI updates in Learning Hub (v1.0.85-1.0.86)

- Add include-custom-instructions frontmatter option for custom agents
- Document context management tools opt-in for agents/subagents (v1.0.85+)
- Document concise transcriptView setting (v1.0.85+)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
2026-09-18 20:53:08 +00:00
committed by GitHub
co-authored by Copilot
parent 4f4796f0bf
commit 752148d0cd
2 changed files with 26 additions and 2 deletions
@@ -3,7 +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: 2026-09-05
lastUpdated: 2026-09-18
estimatedReadingTime: '10 minutes'
tags:
- agents
@@ -108,6 +108,18 @@ tools: ['codebase', 'terminal', 'github']
For MCP server tools, reference them by server name (e.g., `postgres`, `docker`). See [Understanding MCP Servers](../understanding-mcp-servers/) for details.
**include-custom-instructions** *(Copilot CLI v1.0.86+)*: By default, a custom agent's own frontmatter and instructions body fully define its behavior, without automatically pulling in repository-wide instruction files. Set `include-custom-instructions: true` to have the agent also load your repository's instruction files — `AGENTS.md`, `copilot-instructions.md`, and `CLAUDE.md` — layering the agent's specialized persona on top of your team's general coding standards:
```yaml
---
name: 'Security Reviewer'
description: 'Expert security auditor that reviews code for OWASP vulnerabilities'
model: Claude Sonnet 4
include-custom-instructions: true
tools: ['codebase', 'terminal', 'github']
---
```
### Agent Instructions
After the frontmatter, write Markdown instructions that define the agent's behavior. Structure these clearly:
@@ -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: 2026-09-12
lastUpdated: 2026-09-18
estimatedReadingTime: '10 minutes'
tags:
- configuration
@@ -946,6 +946,18 @@ copilot skill enable my-skill # enable a specific skill
*(v1.0.84+)* Command-line parsing moved from Commander to a Rust-based grammar that mirrors what the CLI actually parses, which also generates shell completions directly from that grammar — so `copilot <TAB>` now offers root flags alongside subcommands, and each subcommand only shows its own options. As a result of this change, some error and help wording changed, `copilot login --host` now works correctly, and `--max-autopilot-continues` no longer accepts scientific notation as a value.
### Context Management Tools for Agents and Subagents
*(v1.0.85+)* Opt in to context management tools for agents and subagents from `/settings`, giving agents more direct control over how their context window is curated during long-running sessions.
### Concise Transcript View
*(v1.0.85+)* Set `transcriptView` to `"concise"` to group tool activity into expandable work summaries instead of a flat scrolling log — useful for keeping long sessions readable while still letting you drill into the details of any step.
### Repository Instructions in Custom Agents
*(Copilot CLI v1.0.86+)* Custom agents can opt into repository instruction files by setting `include-custom-instructions: true` in their frontmatter, layering `AGENTS.md`, `copilot-instructions.md`, and `CLAUDE.md` on top of the agent's own persona and instructions. See [Building Custom Agents](../building-custom-agents/) for the frontmatter syntax.
## Common Questions
**Q: How do I disable Copilot for specific files?**