Skip to main content
Use --help with any command to see its arguments and options:

antigen login

Sign in through your browser.
The CLI prints a link and a code and opens the link. Approve the code in your browser, and the CLI prints the organization it signed in to. The session is saved in ~/.antigen/credentials and acts with your role in that organization. When ANTIGEN_API_KEY is set, the CLI uses that key for API requests instead of the session. See CI and automation.

antigen logout

Sign out of the session and delete the saved credentials.
This leaves any ANTIGEN_API_KEY environment variable unchanged.

antigen whoami

Show the email, organization, and role the CLI acts as, and whether it uses a session or ANTIGEN_API_KEY.

antigen targets

List your organization’s targets and their approval status.
See Targets for submitting targets for approval.

antigen run

Start an agent and follow its progress until the run finishes.
Uses tCell by default. To run an agent your team has registered, pass its name:
Configuration options apply to this run. The registered agent’s configuration stays unchanged. For example, add skills from your repository and choose a model:
The CLI reads skill files before starting the run. If --skills is omitted, it uses the agent’s configured skills. With --json, activity and diagnostic messages go to standard error. Add --quiet to suppress activity:
A completed run exits with code 0, including when it discovers vulnerabilities. A failed or stopped run exits with a nonzero code. See CI/CD for failing a check based on vulnerability severity.

antigen runs

List your organization’s runs.

antigen vulnerabilities

List vulnerabilities associated with a run.
Filters apply together. Results reflect each vulnerability’s current status and assignment.

antigen vulnerability push

Create an issue for a vulnerability in your organization’s connected Linear or Jira workspace, the same as Push to Linear or Push to Jira on the vulnerability page.
The CLI prints the issue’s key and URL. Pushing requires the admin role, which API keys have. Pushing the same vulnerability again returns the issue the first push created. The command fails with tracker_not_connected until the tracker is connected under Settings → Integrations.

antigen evidence

List evidence associated with a run.
Use --json to return evidence metadata as a JSON array.

antigen download

Download an evidence item.

antigen steer

Send instructions, context, or a question to an agent.
You can also continue the conversation after testing finishes:
The agent uses the conversation and evidence from that run. See Steering for examples.

antigen stop

Snapshot the run’s sandbox and stop its execution.
The command waits until the snapshot is saved and the sandbox has stopped. Saved vulnerabilities and evidence remain available.

antigen resume

Restore a stopped run’s sandbox and continue with its saved agent configuration.
The run keeps its ID. The CLI streams activity and waits until the run finishes.

antigen open

Open a run in the Antigen platform.

antigen version

Print the installed CLI version.