Copilot Code Review Metrics Now Track Active vs Passive Copilot code review metrics now split active and passive user engagement. Admins can measure real adoption maturity instead of just coverage.
GitHub Copilot CLI's Rubber Duck Uses Cross-Model Review GitHub Copilot CLI's new Rubber Duck feature uses a second AI model family to review agent plans and code. Claude Sonnet + GPT-5.4 closes 74.7% of the performance gap to Opus on difficult multi-file tasks.
How GitHub Cut Pull Request Rendering Time by 78% GitHub rebuilt the Files changed tab from the ground up, cutting React components per diff line from 8 to 2 and slashing interaction latency by 78%. Here's how they did it—and what it means for scaling React apps.
Spec Kit 0.5.0: Documentation & Reference Updates Spec Kit 0.5.0 adds contributor documentation and updates community references. A maintenance release focused on developer experience.
Spec Kit 0.4.5: Claude Code Skills & Plugin Migration Spec Kit 0.4.5 brings Claude Code as native skills, completes the plugin architecture migration with 19 agents moved to TOML, and removes legacy scaffolding.
Spec Kit 0.4.5: Plugin Architecture Complete Spec Kit 0.4.5 completes the plugin architecture migration, removes legacy scaffolding, and adds Claude Code as native skills with 5 new lifecycle extensions.
GitHub's Plan to Stop Supply Chain Attacks on Actions Attackers are exploiting GitHub Actions workflows to steal secrets and publish malicious packages. GitHub is accelerating security features and expanding trusted publishing. Here's what you need to do now.