GitHub Copilot

The Actera plugin connects GitHub Copilot CLI tool requests to your workspace: shell commands, file reads and edits, MCP tools and other local tools. It is tested with the Copilot CLI and with the Copilot agent in VS Code, which picks up plugins installed with the CLI and uses the same connection and mode. The GitHub Copilot app and Copilot in the cloud can also load Copilot plugins; the hooks have not been tested there. Start with Monitoring to inspect the requests and define policies before enforcing them.

Install and connect

In Actera, open Agents → Add agent → GitHub Copilot. Use the installation commands shown there. The current setup uses:

copilot plugin marketplace add Actera-AI/actera-copilot
copilot plugin install actera@actera

Inside Copilot, run:

/actera:connect

Follow the browser connection flow, verify that its code matches the one Copilot displays, and approve the intended agent and workspace. With a setup code from the Overview, run /actera:connect <code> instead; it connects to the agent the code was made for.

Copilot loads a plugin’s hooks when a session starts, so start a new session or run /restart. Then use a tool in Copilot. Actera confirms the first request and shows the agent. If setup was closed, find it under Not set up. /actera:status reports when no hook has run yet.

Configure its authority

New installations default to Monitoring. Review actual action names and arguments in Decisions, create policies from representative requests, and add tests for the boundaries that matter. Copilot actions use Copilot’s own tool names: copilot.tool.<tool> (for example copilot.tool.bash, copilot.tool.powershell, copilot.tool.view, copilot.tool.edit and copilot.tool.apply_patch) and copilot.mcp.<tool>. Which file editing tool Copilot uses depends on the model. apply_patch sends its patch as text, which policies read as action.attributes.parameters.patch. Policies read Copilot’s session details under context.copilot, such as context.copilot.cwd.

Publish and assign the policies, then choose the agent’s When no policy matches setting. Saving this configuration does not itself change the plugin’s mode.

Run /actera:mode in Copilot to choose:

• Mode: Monitoring records results without stopping tools. Enforcing applies Allow, Require approval, and Block.
• When Actera cannot evaluate: in Enforcing, block tool calls by default, or explicitly choose to allow them during an evaluation failure. Allowing them means those calls can run without an authority decision.

The change applies to the next tool call. Confirm that new requests appear as Enforcing in Actera and exercise an allowed and blocked tool call.

Handle approvals

In Enforcing mode a call that needs approval waits while Actera notifies eligible reviewers in Actera, Slack or email. An approval releases the call; a rejection denies it with the reviewer’s reason. After about nine minutes without a decision the call is denied with a link to review it, and an identical retry in the same session within an hour reuses the approval once. Check Needs approval for the request, its reason, and current status.

Approval does not independently prove that the tool ran or completed; review execution reports alongside the decision. Copilot tells the plugin whether each call succeeded or failed, and the plugin reports that as the outcome.

Understand what is sent

The plugin sends tool names and inputs after sensitive-field redaction and secret scanning. Detection is best effort: ordinary commands, file paths, and other non-secret input can remain visible. Prompts and tool output are not sent.

Review the recorded input before broader rollout. Include only tools and environments whose data is appropriate for your workspace.

Manage access

The agent’s Connection panel shows connection status and key expiry. Disconnect stops that key immediately. Run /actera:connect --reconnect to connect this machine again, or /actera:disconnect to remove this machine’s connection.

Policies cover requests that pass through the plugin. Copilot lets a call run when a hook exceeds its timeout, and a disabled plugin checks nothing. For mandatory enforcement, deploy the same hooks as policy hooks on each machine, and verify coverage for the tools your team uses before relying on enforcement.