Code review with GitHub Copilot CLI
GitHub Copilot CLI, GitHub's coding agent, in CodePanel's review loop: it connects through MCP and skills, reads AGENTS.md and answers every finding.
GitHub Copilot CLI is GitHub's coding agent, in the terminal and cloud sandboxes, in public preview. 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, CLAUDE.md and GEMINI.md, and the setup skill writes the loop into AGENTS.md or CLAUDE.md.
How GitHub Copilot CLI connects
GitHub Copilot CLI connects through an MCP server entry in ~/.copilot/mcp-config.json and the codepanel and codepanel-setup skills. The steps are in Other MCP clients.
GitHub Copilot CLI features for the review loop
| Feature | What the docs say | Source |
|---|---|---|
| Maker | GitHub | docs.github.com |
| Runs in | the terminal and cloud sandboxes, in public preview | docs.github.com |
| MCP | Local (stdio), HTTP and SSE servers in ~/.copilot/mcp-config.json or a repository's .mcp.json, added with copilot mcp add --transport http; /mcp auth signs in with OAuth |
docs.github.com, page 2 |
| Hooks | Commands, HTTP calls and prompts set in .github/hooks/*.json or ~/.copilot/hooks/; agentStop runs when the agent finishes responding |
docs.github.com, page 2 |
| GitHub Actions | A documented workflow that installs the CLI with npm and runs copilot -p with COPILOT_GITHUB_TOKEN |
docs.github.com |
| Headless mode | copilot -p "<prompt>", with --allow-all-tools to run tools without asking |
docs.github.com |
| Rules files | AGENTS.md, .github/copilot-instructions.md, .github/instructions/**/*.instructions.md, CLAUDE.md, GEMINI.md |
docs.github.com |
| Models | The models Copilot hosts, from OpenAI, Anthropic, Google, xAI, Moonshot AI and Microsoft, or your own provider's, including local models. Prices: OpenAI, Anthropic, Google, xAI, Moonshot. | docs.github.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.
GEMINI.md for an agent-to-agent review loop
What Gemini CLI loads from GEMINI.md, why it skips AGENTS.md by default, and three ways to give it the same review instructions as every other agent.