GitHub Copilot in VS Code consumes RAC on two surfaces — a generated custom-instructions file Copilot reads, and the lore MCP server its agent mode connects to. A stranger can reproduce this from the file alone.

pip install rac-core   # the `rac` CLI and the `lore` MCP server

A repository with a RAC corpus under decisions/ (run decided quickstart, or use this repository's own decisions/).

decided export decisions/ --agent-rules

Among the agent-context files this writes is .github/copilot-instructions.md — Copilot's repository custom-instructions file — into a managed block (your own content is preserved). Copilot Chat applies it automatically (ensure "Use Instruction Files" / github.copilot.chat.codeGeneration.useInstructionFiles is enabled — on by default in recent VS Code). Re-run on change; decided export decisions/ --agent-rules --check fails CI on drift.

Copilot's agent mode uses MCP servers. Add .vscode/mcp.json in the repo root — note VS Code uses the servers key (not mcpServers); a sample is in mcp.example.json:

{
  "servers": {
    "asdecided": {
      "type": "stdio",
      "command": "decided-mcp",
      "args": ["--root", "."]
    }
  }
}

(Or run MCP: Open User Configuration for a user-level server.) Start it from the MCP view, then use Copilot Chat in Agent mode. It exposes the five read-only lore tools (get_summary, search_artifacts, get_artifact, get_related, find_decisions); the server re-reads the corpus on every call and never writes to the repo.

RAC supplies context and enforces after the edit (ADR-067). No platform API vetoes a Copilot suggestion before it lands, so Copilot relies on the post-edit guard: decided validate / decided relationships --validate and the GitHub Action / pre-merge gate. (The pre-edit veto is Claude-Code-specific — see examples/claude-code/.)

Run the bundled grounding demo — same task twice, once unconnected and once with lore connected — and watch the connected run respect a recorded decision the unconnected run violates: examples/guide/.