mirror of
https://github.com/github/awesome-copilot.git
synced 2026-07-14 01:51:02 +00:00
[bot] Add GPT-5.6, /refine command, plugin dashboard, and v1.0.70 features to Learning Hub (#2258)
* docs: update Learning Hub with v1.0.69-v1.0.70 Copilot features - Add GPT-5.6 model to building-custom-agents.md model table (v1.0.70+) - Add /refine command documentation to copilot-configuration-basics.md (v1.0.70+) - Add --sandbox/--no-sandbox startup flags to copilot-configuration-basics.md (v1.0.70+) - Add .github/copilot/settings.json trusted repo model pinning (v1.0.70+) - Add SHA pinning for marketplace registrations to installing-and-using-plugins.md (v1.0.70+) - Add /plugins interactive dashboard to installing-and-using-plugins.md (v1.0.69+) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Update website/src/content/docs/learning-hub/installing-and-using-plugins.md --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Aaron Powell <me@aaron-powell.com>
This commit is contained in:
github-actions[bot]
committed by
GitHub
GitHub
parent
30472ecf0f
commit
f8d98b41d1
@@ -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: 2026-07-06
|
||||
lastUpdated: 2026-07-09
|
||||
estimatedReadingTime: '10 minutes'
|
||||
tags:
|
||||
- agents
|
||||
@@ -256,6 +256,7 @@ The agent can then query your database, analyze query plans, and suggest optimiz
|
||||
|----------|-------------------|
|
||||
| Most demanding reasoning, security review | Claude Sonnet 5 *(v1.0.67+)* |
|
||||
| Complex reasoning, analysis | Claude Sonnet 4 |
|
||||
| Code generation, tool-driven agentic work | GPT-5.6 *(v1.0.70+)* |
|
||||
| Code generation, refactoring | GPT-4.1 |
|
||||
| Code-specialized tasks, large context | kimi-k2.7-code *(v1.0.68+)* |
|
||||
| Quick analysis, simple tasks | Claude Haiku or GPT-4.1-mini |
|
||||
|
||||
@@ -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: 2026-07-07
|
||||
lastUpdated: 2026-07-09
|
||||
estimatedReadingTime: '10 minutes'
|
||||
tags:
|
||||
- configuration
|
||||
@@ -207,6 +207,32 @@ In addition to repository-level skills, GitHub Copilot CLI supports **personal s
|
||||
|
||||
The `~/.agents/skills/` path aligns with the VS Code GitHub Copilot for Azure extension's default skill discovery path, while `~/.copilot/skills/` matches the Copilot CLI configuration directory. Both are supported for personal skills.
|
||||
|
||||
### Pinning Model and Effort via `.github/copilot/settings.json`
|
||||
|
||||
*(v1.0.70+)* A **trusted repository** can pin the model, reasoning effort level, and context tier for all sessions working in that repository by adding a `.github/copilot/settings.json` file. This is a team governance feature that ensures everyone uses a consistent model configuration without relying on individual user settings:
|
||||
|
||||
```json
|
||||
{
|
||||
"model": "claude-sonnet-4",
|
||||
"effortLevel": "high",
|
||||
"contextTier": "full"
|
||||
}
|
||||
```
|
||||
|
||||
**Supported fields**:
|
||||
|
||||
| Field | Description | Example values |
|
||||
|-------|-------------|----------------|
|
||||
| `model` | The AI model to use for this repository | `"claude-sonnet-4"`, `"gpt-4.1"`, `"claude-sonnet-5"` |
|
||||
| `effortLevel` | Reasoning effort level | `"low"`, `"medium"`, `"high"` |
|
||||
| `contextTier` | How much context to include | `"default"`, `"full"` |
|
||||
|
||||
In addition to model and effort settings, this file can also extend the URL, MCP server, and skill deny lists, allowing organizations to enforce access restrictions at the repository level.
|
||||
|
||||
**Why use this**: Pin a model when your team has agreed on the right cost/quality tradeoff for a project. Pin a high effort level for codebases where mistakes are expensive. Deny lists let you block specific MCP servers or URLs that aren't appropriate for a given project's security posture.
|
||||
|
||||
> **Trust requirement**: The repository must be explicitly trusted by the user for these settings to take effect. This prevents untrusted repositories from changing your model or access restrictions without your knowledge.
|
||||
|
||||
### Custom Agents
|
||||
|
||||
Agents are specialized assistants for specific workflows. Place agent definition files in `.github/agents/`.
|
||||
@@ -592,6 +618,14 @@ The `/ask` command lets you ask a quick question without affecting your conversa
|
||||
/ask What does the `retry` utility in src/utils do?
|
||||
```
|
||||
|
||||
The `/refine` command *(v1.0.70+)* rewrites a rough, stream-of-consciousness prompt into a clear, structured one before sending it to the agent:
|
||||
|
||||
```
|
||||
/refine
|
||||
```
|
||||
|
||||
Type your rough idea, and `/refine` transforms it into a precise, well-structured prompt. This is especially helpful for complex multi-step tasks where prompt clarity significantly affects output quality — for example, turning "um make the login thing work better with the existing setup" into a focused task description with clear scope and acceptance criteria.
|
||||
|
||||
The `/env` command shows all loaded environment details — instructions, MCP servers, skills, agents, and plugins — in a single view. Use it to verify that the right resources are active for the current session:
|
||||
|
||||
```
|
||||
@@ -697,6 +731,15 @@ copilot --autopilot --max-autopilot-continues 10 "Refactor the authentication mo
|
||||
|
||||
Set it higher for long-running tasks, or lower for tasks where you want more frequent checkpoints. Setting it to `0` disables automatic continuation entirely.
|
||||
|
||||
The `--sandbox` and `--no-sandbox` flags *(v1.0.70+)* turn the OS-level shell sandbox on or off for the current session only, without permanently changing your saved sandbox setting. This is useful with `-p` (prompt mode) when you need to temporarily adjust sandbox behavior for a specific automated task:
|
||||
|
||||
```bash
|
||||
copilot --sandbox -p "Run the full test suite and fix any failures"
|
||||
copilot --no-sandbox -p "Set up development environment with system tools"
|
||||
```
|
||||
|
||||
These flags apply only to the current invocation — your persisted sandbox preference remains unchanged.
|
||||
|
||||
The `--attachment` flag (available in prompt mode, `-p`) lets you attach files — images or native documents — to the initial prompt in non-interactive mode:
|
||||
|
||||
```bash
|
||||
|
||||
@@ -3,7 +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: 2026-06-24
|
||||
lastUpdated: 2026-07-09
|
||||
estimatedReadingTime: '8 minutes'
|
||||
tags:
|
||||
- plugins
|
||||
@@ -160,6 +160,28 @@ To automatically register an additional marketplace for everyone working in a re
|
||||
|
||||
With this in place, team members automatically get the `my-org-plugins` marketplace available without running a separate `marketplace add` command. This replaces the older `marketplaces` setting, which was removed in v1.0.16.
|
||||
|
||||
### Pinning a Marketplace to a Specific Commit
|
||||
|
||||
*(v1.0.70+)* To ensure reproducibility and prevent unintended updates, you can pin a marketplace to an exact commit SHA using the `sha` field in the source configuration:
|
||||
|
||||
```json
|
||||
{
|
||||
"extraKnownMarketplaces": [
|
||||
{
|
||||
"name": "my-org-plugins",
|
||||
"source": "my-org/internal-plugins",
|
||||
"sha": "a1b2c3d4e5f6..."
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Pinning to a SHA guarantees that everyone on the team installs plugins from exactly that snapshot of the marketplace, regardless of subsequent changes to the repository. This is useful for:
|
||||
|
||||
- **Reproducible CI environments** — ensure builds always use the same plugin versions
|
||||
- **Change control** — review and approve plugin updates before rolling them out team-wide
|
||||
- **Stability** — prevent breaking changes in upstream marketplaces from impacting your team without notice
|
||||
|
||||
## Installing Plugins
|
||||
|
||||
### From Copilot CLI
|
||||
|
||||
Reference in New Issue
Block a user