Code review with Copilot in VS Code
Copilot in VS Code, GitHub's coding agent, in CodePanel's review loop: it connects through MCP and a setup prompt, reads AGENTS.md and answers every finding.
Copilot in VS Code is GitHub's coding agent, in VS Code's Chat view and the Agents window in a browser, for remote sessions. With CodePanel it is the author on the other side of the review: after it pushes, it reads the panel's findings on that commit over MCP, fixes or disputes each one with evidence, and rates every finding. It reads AGENTS.md, .github/copilot-instructions.md, .github/instructions/**/*.instructions.md and CLAUDE.md (in the Local harness), and the setup prompt writes the loop into AGENTS.md or CLAUDE.md.
How Copilot in VS Code connects
Copilot in VS Code connects through an MCP server entry and the repository setup prompt, pasted into its agent mode. The steps are in VS Code and GitHub Copilot.
Copilot in VS Code features for the review loop
| Feature | What the docs say | Source |
|---|---|---|
| Maker | GitHub | docs.github.com |
| Runs in | VS Code's Chat view and the Agents window in a browser, for remote sessions | code.visualstudio.com, page 2 |
| MCP | HTTP servers with OAuth, falling back to SSE, in .vscode/mcp.json or added with code --add-mcp |
code.visualstudio.com, page 2 |
| Hooks | Agent hooks, in preview; Stop fires when the agent is about to stop |
code.visualstudio.com, page 2 |
| Rules files | AGENTS.md, .github/copilot-instructions.md, .github/instructions/**/*.instructions.md, CLAUDE.md (in the Local harness) |
code.visualstudio.com |
| Models | Models from OpenAI, Anthropic, Google, Microsoft, Moonshot AI and xAI, plus your own key for more, including local models. Prices: OpenAI, Anthropic, Google, xAI, Moonshot. | code.visualstudio.com, page 2 |
Each row was checked on 2026-10-17 against the maker's docs it cites. A feature with no row is one those docs don't describe.
Read next
AGENTS.md for an agent-to-agent review loop
What to put in AGENTS.md so a coding agent answers AI code review on its own: how each agent loads the file, the review section, and one file for every agent.
CLAUDE.md for an agent-to-agent review loop
What to put in CLAUDE.md so Claude Code sees AI code review through to merge: what loads when, where the loop goes, the size target, and sharing with AGENTS.md.
copilot-instructions.md for an agent-to-agent review loop
How GitHub Copilot CLI and Copilot in VS Code combine copilot-instructions.md with AGENTS.md, CLAUDE.md and GEMINI.md, and where the review loop belongs.