Skip to main content
Corridor integrates with the cloud environments behind Claude Code on the web and Claude Tag, Anthropic’s @Claude in Slack, to catch security vulnerabilities before code is committed. When configured, every session installs the Corridor CLI and a git pre-commit hook that scans staged changes and blocks commits containing security findings.

​
Prerequisites

  • A Corridor account with a team created
  • Owner role on your Corridor team
  • A Claude account with permission to edit cloud environments
  • The repository imported into Corridor as a project

​
Setup

1

Open the Long-Running Agents page in Corridor

In the Corridor dashboard, navigate to Governance > Long-Running Agents and click the Configuration tab.Select Claude Code from the agent options.
2

Open your Claude cloud environment settings

Go to claude.ai/admin-settings/cloud-environments and select the environment you want to configure or create a new one.Set the environment’s Network access to Full access. The setup script downloads the Corridor CLI over the network, and Trusted access only reaches package managers and MCP servers.
3

Generate a Corridor API key

Back in the Corridor Configuration tab, enter a name for your key (for example, “Claude cloud agents”) and click Generate key.Corridor shows the finished setup command with the key already in it. Copy the whole command, and note that the key is only shown once.
4

Paste the setup command

In your Claude cloud environment settings, paste the command into the Setup script field and save:
If you are reusing an existing key, paste this template and replace YOUR_KEY with it.The script runs at the start of every session. It installs the Corridor CLI and a git pre-commit hook that runs corridor scan --staged before each commit.
5

Point your sessions at this environment

​
How it works

Once configured, every Claude Code cloud session will:
  1. Install the Corridor CLI
  2. Install a git pre-commit hook
  3. Scan staged changes before each commit
  4. Block commits that contain security findings
Sessions start from a fresh clone before the hook could be installed in a repository, so it goes in the home directory and covers the checkout the session creates afterwards. Findings caught by the pre-commit scan appear in the Usage tab of the Long-Running Agents page, where you can review severity, affected files, and resolution status.

​
Managing API keys

You can view and revoke API keys in the Configuration tab under Team-Owned API Keys. Each key shows its name, creation date, and last used date. To rotate a key:
  1. Generate a new key in Corridor
  2. Replace the key in the Setup script command in your Claude cloud environment settings
  3. Revoke the old key

​
Next steps

Guardrails

Configure the security rules that your agents enforce.

Findings

Learn how to review and resolve security findings.