I tested Claude Code, Codex, and OpenCode on real full-stack work: a Next.js feature, a backend bug, a legacy refactor, and ...

Visual Studio Code 1.129 adds a dedicated process for running AI agent sessions and an experimental docked editor for reviewing agent-generated changes.

Microsoft is keeping Visual Studio's new built-in Agent Skills switched off by default while a public dashboard measures whether their performance gains justify the additional tokens they may consume.

What you get is a system that works in five different ways simultaneously, none of which were designed to coexist.