node9 with GitHub Copilot CLI

Control modelhooks + MCPSees every tool callyesPrompt scanningyes

node9 sees every tool call GitHub Copilot CLI makes, through a pre-execution hook, and governs its MCP servers too. A risky action is allowed, sent to you for review, or blocked before it runs.

Copilot CLI is wired on three events, which makes it one of the strongest integrations.

SurfaceHow node9 is wiredWhat it does
Every tool callPreToolUse in ~/.copilot/hooks/node9.jsonallow / review / block before the tool runs
Every tool resultPostToolUseaudit record
Pasted promptsUserPromptSubmitprompt secret scan
MCP servers~/.copilot/mcp-config.json entries are wrappedper-tool allow / review / block

Set it up

node9 agents add copilot

node9 init does this for every agent it detects on the machine. Either command is safe to re-run; it repairs a hook that an agent update removed and leaves everything else alone.

What is not covered

  • Cost is not tracked for Copilot.
  • Tool output is observed, not gated.

Verify it on this machine

node9 doctor                                   # is the hook (or MCP wrap) actually in place?
node9 explain Bash 'cat ~/.ssh/id_rsa'         # shows the verdict the live hook enforces: BLOCK

node9 explain prints the exact rule that fires and where the decision came from. If doctor says the agent is not wired, the guard is not running, whatever the config looks like.

Every agent, side by side

node9 wires into twelve agents and the depth differs. The coverage matrix shows all of them in one table, including which ones node9 cannot see the shell of.