Browse All GitHub Copilot Content (396)
GitHub shows how GitHub Copilot CLI can scan a repository and generate a pull request that follows contribution guidelines, issue templates, and team rules—reducing the manual work of formatting and filling out PR details.
Rob Bos covers GitHub Copilot’s token-based billing, focusing on what “tokens” mean in practice and how usage-based pricing can affect Copilot costs for teams and organizations.
Microsoft Developer hosts a Cosmos DB Conf 2026 session where Sergiy Smyrnov demonstrates migrating an AdventureWorks-based ASP.NET/EF Core app from a relational database to Azure Cosmos DB for NoSQL, using GitHub Copilot and Cosmos DB Agent Kit prompts to plan the move and rewrite the data layer.
Mark Downie covers the April Visual Studio 2026 update, focusing on GitHub Copilot’s new cloud agent workflow, user-level custom agents, and a Debugger Agent that validates fixes against real runtime behavior, plus improvements to C++ agent tools, IntelliSense vs Copilot completion priority, and configurable Copilot shortcuts.
JennyF explains how Microsoft’s 1ES team uses agentic AI (including GitHub Copilot CLI) plus “skills” and “agent signals” to speed up CVE remediation and compliance work across many repositories, while keeping humans in the loop for review, validation, and deployment.
Allison announces that GitHub Copilot Student is removing GPT-5.3-Codex from the model picker, while keeping it available via auto model selection. The post explains this as part of temporary reliability/performance measures and points to documentation on supported models and upcoming usage-based billing changes.
Allison shares a GitHub Changelog update: Copilot cloud agent now starts over 20% faster by using optimized runner environments prebuilt with GitHub Actions custom images, reducing environment startup overhead when Copilot begins work from issues, PRs, or the Agents tab.
Allison announces a billing change for GitHub Copilot code review: starting June 1, 2026, reviews will consume both Copilot AI Credits and (for private repos) GitHub Actions minutes, with guidance on checking usage, budgets, and runner configuration.
Mario Rodriguez announces that GitHub Copilot plans will move to usage-based billing on June 1, 2026, replacing premium request units with GitHub AI Credits based on token usage. The post explains what changes for individuals and organizations, including pooled credits, budget controls, and how Copilot code review also uses GitHub Actions minutes.
B_Manasa explains how GitHub Copilot (especially Copilot Chat in VS Code) can speed up relational data modeling by turning architecture intent into reviewable schema drafts faster, using a multi-tenant SaaS control-plane example and concrete prompt patterns for iterating on cardinality, history tables, and schema evolution.
This week’s roundup is about the trade-offs that show up when agents move from demos to daily work: more surfaces, more automation, and more reasons to enforce limits and policies. GitHub Copilot expanded agent experiences and model options (including GPT-5.5 GA), but it also introduced tighter individual usage controls and shifting access to premium Claude Opus models. On the Microsoft side, Azure AI Foundry, Agent Framework, and Fabric leaned into governed tool execution through MCP, with secure networking, managed identity, and outbound restrictions becoming default expectations. We close with the less glamorous but essential work of reliability and security: upcoming GitHub protocol and token changes, DevSecOps tuning via CodeQL and dependency graphs, and Defender research that turns real intrusion chains into actionable hunts and containment steps.
Hidde de Smet's Blog breaks down the difference between AGENTS.md (repo-wide, always-on instructions for coding agents) and .agent.md (custom agent profiles for GitHub Copilot), including where to place each file, what fields matter, and how to use roles, tool restrictions, and handoffs safely.
Visual Studio Code features Reynald Adolphe demonstrating how to create and use Custom Agents in VS Code (Agent Mode) so GitHub Copilot can take on specialized roles—like a security reviewer—using your project context, tools, and workflow to produce more focused results.
Visual Studio Code features Reynald Adolphe explaining how Agent Skills in VS Code package instructions, scripts, and resources into reusable workflows, with a quick demo of creating and modifying a skill to automate multi-step tasks like updating docs and generating prompts.
Visual Studio Code features Reynald Adolphe using GitHub Copilot in VS Code to explain and compare customization features—Custom Instructions, Prompt Files, Agent Skills, Custom Agents, and Hooks—plus ways to learn them via charts, quizzes, and scenario-based references.
Visual Studio Code features Reynald Adolphe explaining GitHub Copilot Hooks in VS Code: how to run commands automatically at specific lifecycle events during an agent session to keep formatting, validations, and scripts consistent without manual steps.
Visual Studio Code shows how to use Prompt Files in VS Code to stop rewriting the same GitHub Copilot instructions, making repeatable workflows (like quizzing open files or simplifying code) easier to run and share across projects and teams.
Visual Studio Code features Reynald Adolphe explaining how GitHub Copilot Custom Instructions in VS Code work in practice, showing how to create reusable “rulebooks” that steer Copilot toward your coding standards, conventions, and preferences (including SOLID and accessibility) without repeating guidance every time.
Visual Studio Code shows how to customize AI in VS Code using agent-based building blocks—agents, skills, instructions, prompt files, and hooks—so teams can reuse prompts, enforce standards, and streamline common development tasks.
Visual Studio Code shows Reynald building a “Repo Analyzer” app in VS Code using GitHub Copilot customization features—Prompt Files, Custom Instructions, Agent Skills, Custom Agents, and Hooks—to enforce repo standards, update docs, and streamline coding tasks in one workflow.