Luci for GitHub Copilot.

Copilot Chat reads .github/copilot-instructions.md for repository instructions. Pass --agents copilot and Luci adds a managed block there with your project's rules, design baseline and active task; the local luci-mcp server gives Copilot your captures, design checks and the feedback you pin on the running page.

What GitHub Copilot gets

Instead of guessing from screenshots and long descriptions, GitHub Copilot works from files in your project and a local MCP server:

  • Project memory. Rules, decisions, the playbook and the active task in .luci/, linked from .github/copilot-instructions.md.
  • Your design system. luci capture baseline writes your type, colours and spacing from your stylesheets, so GitHub Copilot reuses your tokens instead of inventing new ones.
  • Measured references. Components, text styles, colours and spacing captured with the dev toolbar or the extension, saved as .design.md files.
  • Pinned feedback. Notes you click onto the running page. In React, Vue and Svelte projects each one carries its component and source line.
  • Design checks. A part-by-part comparison of what GitHub Copilot built against the capture.

1. Initialize Luci

Run this in your project root. It needs Node 18 or later:

npx @luci-dev/cli@latest init --agents copilot

Luci detects your framework and stylesheets, creates .luci/ and writes its block into .github/copilot-instructions.md. The --agents flag adds GitHub Copilot; combine agents with commas, or pass --agents all.

Luci only edits the lines between its <!-- LUCI and <!-- END LUCI --> markers. Anything you write elsewhere in .github/copilot-instructions.md stays as it is when luci update runs.

2. Connect luci-mcp

luci-mcp (from @luci-dev/mcp) runs on your machine over standard stdio, with no network calls. In VS Code, add the server to .vscode/mcp.json in your project:

.vscode/mcp.json
{
  "servers": {
    "luci": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@luci-dev/mcp"]
    }
  }
}

MCP tools are available to Copilot in agent mode.

The tools GitHub Copilot uses most:

get_project_context
Rules, context and project setup, read at the start of a task.
list_captures · get_capture
The saved .design.md references, read before writing UI.
get_feedback_prompt · watch_feedback
Your pending notes from every page, or new ones as you save them.
get_design_checks
Recent design check results, read after edits.

Every tool is listed in the Agents and MCP docs.

3. Show it what to change

Start the dev toolbar while your app is running, then point at the page instead of describing it:

npx @luci-dev/cli@latest serve

Then ask GitHub Copilot, for example:

  • “Read the pending Luci feedback and fix every item, then report each ID.”
  • “Watch for new Luci feedback while I review the app.”
  • “Build the pricing card from the saved Luci capture, using our tokens.”
  • “Run the design checks again and fix what still differs.”

How notes, layout plans and checks work is in the Devtool guide.

Check the setup

luci doctor checks the installation and project setup and says what to fix. After upgrading Luci, luci update refreshes .github/copilot-instructions.md and the other agent files.

Using more than one agent? They all read the same .luci/ memory. Set up Claude Code, Cursor, Codex or Gemini CLI the same way.