Claude Code

The Actera plugin connects Claude Code tool requests to your workspace. Start with Monitoring to inspect the requests and define policies before enforcing them.

Install and connect

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

claude plugin marketplace add Actera-AI/actera-claude-code
claude plugin install actera@actera --scope user

Inside Claude Code, run /reload-plugins or start a new session, then run:

/actera:connect

Follow the browser connection flow, verify that its code matches the one Claude Code displays, and approve the intended agent and workspace.

Use a tool in Claude Code. Actera confirms the first request and shows the agent. If setup was closed, find it under Not set up.

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. Reconnecting preserves the plugin’s settings.

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.

Open Claude Code’s /config panel 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.

After changing settings, run /reload-plugins or start a new session. Use /actera:status to check effective settings and delivery status. Confirm that new requests appear as Enforcing in Actera and exercise an allowed and blocked tool call.

Handle approvals

A Require approval result in Enforcing mode must pause the tool. Eligible reviewers respond through the supported approval flow. Check Needs approval for the request, its reason, and current status.

The supported inline approval flow offers Allow once or Deny while holding the original call. Approval still requires an eligible reviewer and does not override Claude Code’s own permissions. Approval does not independently prove that the tool ran or completed; review execution reports alongside the decision.

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 responses 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 to establish a new connection.

Policies cover requests that pass through the plugin. Tools or execution paths that bypass it are outside that boundary. Verify coverage for the tools your team uses before relying on enforcement.