This update brings several improvements to GitHub Copilot in JetBrains IDEs. These include support for Agent Skills in preview, several user experience improvements across inline chat and settings, and quality enhancements for a smoother development workflow.

What’s new

Skills support in Agent Mode in public preview

Agent mode now supports skills to help tailor Copilot for your workflows, reduce repeated setup, and load skill-specific content into context when needed. You can create your own skills for your projects or use those shared by the community, such as the github/awesome-copilot repository or the anthropics/skills repository.

[NOTE]
Agent Skills support in Copilot for JetBrains IDEs is currently in public preview. You can enable Agent Skills in your JetBrains IDE via Settings > GitHub Copilot > Chat > Agent.
If you’re a Copilot Business or Copilot Enterprise subscriber, an administrator will have to enable the Editor preview features policy before you can use it. Learn more in our documentation.

User experience enhancements

Inline chat improvements

We’ve introduced several improvements to make inline chat easier to use:

• Quickly add the selected code to Copilot Chat as contextual input

• Open inline chat directly from the floating code toolbar

Refined settings management

The Copilot settings experience has been refined to provide clearer navigation and structure.

• Toggle individual agents: The updated Copilot settings page offers individual toggles, allowing you to enable or disable Agent mode, Coding Agent and Custom Agent independently.
• Sign-in reminder: You’ll see a sign-in reminder in settings if you’re not authenticated.

We’ve also made a few additional usability improvements, including:

• Smoother file navigation when collapsing or expanding files, helping keep conversations organised.
• More intuitive prompt navigation with Home and End keys moving the cursor to the start or end of lines.
• Redesigned chat and diff views for better readability.

Quality improvements

Quality and reliability are also among our top priorities. We’ve made several improvements, including enhanced safety checks in file‑handling tools, increased stability for next edit suggestions, and persistent mode settings after restart.

Try it out

We encourage you to try out the latest version of the GitHub Copilot plugin and share your feedback. Your input is invaluable in helping us refine and improve the product.

Share your feedback

Your feedback drives improvements. We’d love to hear about your experience in the following channels:

• In-product feedback: Use the feedback options within your IDE
• Feedback Repository: Share your thoughts in the GitHub Copilot for JetBrains IDEs issues

The post New features and improvements in GitHub Copilot in JetBrains IDEs appeared first on The GitHub Blog.

We’ve updated the GitHub status page to make incident information easier to find and more useful during an active event. The status site now includes a 90-day historical view of availability and clearer linking between availability trends and the incidents that occurred on specific days. This change rolled out to all regions in which GitHub operates.

Looking forward

When an incident occurs, we’re working toward publishing more specific impact details. This includes:

• GitHub Actions: identifying the affected runner environment (for example, GitHub-hosted vs. self-hosted).
• GitHub Copilot: identifying the affected Copilot surface area (completions, chat, agent) and, where applicable, the specific model(s) impacted.

The post Updated GitHub status page experience appeared first on The GitHub Blog.

Enterprise and organization admins can now choose whether profile names (first and last name) appear alongside usernames across GitHub enterprise, including in repositories, issues, pull requests, and discussions. The setting applies to public, private, and internal repositories within your enterprise’s organizations.

To manage configure user display name at the enterprise level:

1. In the top-right corner of GitHub, click your profile picture.
2. Depending on your environment, click Enterprise, or click Enterprises then click the enterprise you want to view.
3. At the top of the page, click Settings.
4. On the “Manage your enterprise profile” page, go to “Member appearance”.
5. Under “Profile name visibility”, select one of the following options in the adjacent dropdown list.
   — Enable everywhere
   — Disable everywhere
   — Let organizations decide

Note: When enabled or disabled at the enterprise level, this policy is applied across all organizations within your enterprise.

To manage configure user display name at the organization level:

1. In the upper-right corner of GitHub, click your profile picture, then click Organizations.
2. Next to the organization, click Settings.
3. On the “Manage your enterprise profile” page, go to “Member appearance”.
4. Under “Profile name visibility”, select one of the following options in the toggle.
   — On
   — Off

Note: The organization-level setting will only be configurable if the enterprise-level policy is set to Let organizations decide

Learn more in our enterprise account documentation.

The post Show profile names (first and last name) alongside user handles appeared first on The GitHub Blog.

Maintainers now have more control over how repositories accept contributions. Two new settings let you manage pull requests to better match your project’s needs.

Disable pull requests entirely

You can now turn off pull requests entirely from your repository’s Settings, just like you can with wikis, issues, discussions, and projects. When disabled, the pull requests tab will not be visible. This means no one can see existing pull requests or open new ones.

This is particularly useful for mirror repositories, read-only codebases, or projects where you want to share your work publicly without managing contributions.

Restrict pull requests to collaborators

You can now restrict pull request creation to collaborators only if you still want to use the pull request flow with a managed group of contributors. When enabled, the pull requests tab remains visible. All pull requests can be seen and commented on, but only collaborators (i.e., users with write access) can create new ones. Collaborators can be added or removed by going to the Collaborators tab in a repository’s settings.

This helps you manage contribution quality during critical development phases or when you need tighter control over who submits changes.

Availability

These settings are available now for all public and private repositories. Navigate to your repository’s Settings > General > Features to configure pull request access.

Mobile app: Full UI changes are coming soon to the mobile app. Currently if you disable pull requests, the pull requests tab will still appear in the app, but no one can create new pull requests. All other settings work the same across both platforms.

Note: To temporarily limit activity from certain users on a public repository, you can continue to use temporary interaction limits.

Learn more about managing pull request settings

For a deeper dive on why we’re doing this and our broader efforts, check out our latest blog post. To share your feedback, join the conversation in our Community discussion.

The post New repository settings for configuring pull request access appeared first on The GitHub Blog.

Copilot coding agent is our asynchronous, autonomous background agent. Delegate a task to Copilot, and Copilot works in the background in its own development environment, powered by GitHub Actions. Once Copilot finishes work, it opens a pull request and requests your review.

We’re making some changes to the network configuration for Copilot coding agent which will take effect at 00:00 UTC on February 27, 2026. These changes affect teams who have configured the agent to run on self-hosted runners or larger runners with Azure private networking.

If you have run at least one Copilot coding agent session on a self-hosted runner or larger runner with Azure private networking in the past 60 days, you will receive an email notification today with a list of potentially-affected repositories to review.

What’s changing

Today, Copilot coding agent connects to api.githubcopilot.com to access AI inference and stream logs to GitHub.

From February 27, 2026 at 00:00 UTC, Copilot will apply subscription-based network routing, connecting to a different host depending on the Copilot plan of the user who initiated the agent task:

• Copilot Business: api.business.githubcopilot.com
• Copilot Enterprise: api.enterprise.githubcopilot.com
• Copilot Pro and Pro+: api.individual.githubcopilot.com

Next steps

If you’ve received an email notification or you believe you may be affected, identify repositories that are using Copilot coding agent with affected runner types.

You can identify the runners used for Copilot coding agent in a repository by checking the runs-on value in the .github/workflows/copilot-setup-steps.yml file. If there is no copilot-setup-steps.yml file, the repository is not affected.

Next, review the network configuration for those runners and ensure that Copilot is able to connect to the new host(s) above by February 27, 2026. You may need to allow multiple hosts if users are subscribed to different Copilot plans.

If you don’t make this change by February 27, 2026, Copilot coding agent tasks may fail because the agent runtime will be unable to communicate with GitHub systems.

The post Network configuration changes for Copilot coding agent appeared first on The GitHub Blog.

GitHub Agentic Workflows let you automate repository tasks using AI agents that run within GitHub Actions. Write workflows in plain Markdown instead of complex YAML, and let AI handle intelligent decision-making for issue triage, pull request reviews, CI failure analysis, and repository maintenance.

By adding Markdown files to .github/workflows/, you can describe automation goals in natural language. The gh aw CLI converts these into standard GitHub Actions workflows that execute using GitHub Copilot CLI or other coding agents. Workflows run with read-only permissions by default and use preapproved “safe outputs” for write operations.

The feature is available in technical preview through the gh aw CLI extension.

Demo

Key benefits

• Natural language workflows: Write automation in Markdown instead of YAML. Describe what you want in natural language, and the AI agent figures out how to do it.
• Security-first design: Read-only by default with sandboxed execution, network isolation, SHA-pinned dependencies, and sanitized write operations through safe outputs.
• Multiple coding agents: Works with GitHub Copilot CLI (default) or other AI coding agents. Same workflow format across all engines.
• Deep GitHub integration: Native access to repositories, issues, pull requests, actions, and security through the GitHub MCP Server. Additional tools for browser automation, web search, and custom MCPs.
• Flexible triggers: Respond to issues and pull request events, run on schedules, dispatch manually, or invoke via commands in comments.
• Easy to start: Install the CLI extension, create a Markdown file, compile, and commit. They run as standard GitHub Actions.
• Agentic authoring: Create, edit, debug, and optimize workflows using AI agents in VS Code, github.com, or your preferred coding agent.
• Open source: Fully open source on GitHub under the MIT license. Community contributions are welcome.

Examples

Imagine repository automation that automatically triages incoming issues, investigates root causes of CI failures, maintains documentation, improves test coverage, monitors compliance, and even boosts team morale. With agentic workflows, you define these behaviors in simple Markdown files.

Not sure where to begin? Check out Peli’s Agent Factory which showcases over 50 specialized agentic workflows for different use cases.

Getting started

Learn more by reading the GitHub Agentic Workflows documentation. See what others are building, join the discussion and share your thoughts and feedback in the Community and in the GitHub Next Discord.

GitHub Agentic Workflows are a collaboration among GitHub Next, Microsoft Research, and Azure Core Upstream. The implementation is open source on GitHub in the gh-aw repository.

Read more on the GitHub Blog post introducing Agentic Workflows.

The post GitHub Agentic Workflows are now in technical preview appeared first on The GitHub Blog.

Copilot Pro and Pro+ subscribers can now choose a model when starting a Copilot coding agent session in the GitHub Mobile app. You can quickly match the model to the task at hand without needing to switch to desktop. Maybe you want to opt for faster responses when you’re on the go, or you want to pick a more capable model for deeper work.

When you start a session in the app, use the model picker to select from:

• Auto
• Anthropic Claude Opus 4.5
• Anthropic Claude Opus 4.6
• Anthropic Claude Sonnet 4.5
• OpenAI GPT-5.1-Codex-Max
• OpenAI GPT-5.2-Codex

If you leave it on Auto, Copilot will automatically select a model to optimize for speed and performance based on availability.

This model picker is available now for Copilot Pro and Pro+ subscribers. Support for Copilot Business and Enterprise is coming soon.

To learn more, see the documentation on model selection for Copilot coding agent.

The new experience is now available on the latest production build of GitHub Mobile on iOS and Android.

Join the discussion within GitHub Community.

The post GitHub Mobile: Model picker for Copilot coding agent appeared first on The GitHub Blog.

Two new event types are now available to track changes to Dependabot settings through your organization and enterprise audit logs.

• Dependabot vulnerability updates toggle logs when someone enables or disables Dependabot vulnerability updates on a repository. Learn more in our dependabot_security_updates documentation.
• Self-hosted runner configuration logs when someone enables or disables Dependabot on self-hosted runners. Learn more in our repository_dependency_updates_self_hosted documentation.

Each event captures the actor who made the change and when it occurred. You’ll find these events in your organization audit log or enterprise audit log. This new data allows you to:

• Track configuration changes for compliance and auditing purposes.
• Identify unauthorized modifications to security settings.
• Perform forensic investigations when needed.

Join the discussion in the GitHub Community.

The post Track additional Dependabot configuration changes in audit logs appeared first on The GitHub Blog.

GPT-5.3-Codex, OpenAI’s latest agentic coding model, is now rolling out in GitHub Copilot. In early testing, GPT-5.3-Codex reaches new high scores on benchmarks we use to evaluate coding, agentic, and real-world capabilities. It also has improved reasoning and execution in complex, tool-driven, long-running workflows which help it to deliver up to 25% faster performance than GPT-5.2-Codex on agentic coding tasks.

Availability in GitHub Copilot

GPT-5.3-Codex will be available to Copilot Pro, Pro+, Business, and Enterprise users.

You’ll be able to select the model in the model picker in:

• Visual Studio Code in all modes: chat, ask, edit, agent
• github.com
• GitHub Mobile iOS and Android
• GitHub CLI
• GitHub Copilot Coding Agent

Rollout will be gradual. Check back soon if you don’t see it yet.

Enabling access

Copilot Enterprise and Copilot Business plan administrators must enable the GPT-5.3-Codex policy in Copilot settings.

Learn more

To explore all models available in GitHub Copilot, see our documentation on available models and get started with Copilot.

Share your feedback

Join the GitHub Community to share your feedback.

The post GPT-5.3-Codex is now generally available for GitHub Copilot appeared first on The GitHub Blog.

GitHub Enterprise administrators can now use GitHub Apps with the enterprise teams fine-grained permissions to access Enterprise Teams API endpoints. Previously, these endpoints required a personal access token (classic), but this update provides a more secure approach for enterprise team management.

The new enterprise teams fine-grained permission offers both read and write access levels to an enterprise-level Github App. These new fine-grained permissions allow create, update, and delete operations enabling Enterprise administrators to securely manage their teams at scale with programmatic app integrations.

To learn more, read about GitHub Apps authentication or Enterprise Teams API endpoints. If you have feedback, join us in this discussion.

The post GitHub Apps can now utilize public preview Enterprise Teams APIs via fine-grained permissions appeared first on The GitHub Blog.