Agent mode
--agent is a one-flag bundle equivalent to --output json --non-interactive --quiet with audio autoplay disabled. Successful JSON results go to stdout; error envelopes go to stderr. Read the JSON payload and exit code. Do not parse status text.
Exit codes
Exit codes are stable across releases. Branch on them to choose a recovery action: retry onnetwork, top up on quota, or re-authenticate on auth.
| Code | Value | Meaning |
|---|---|---|
success | 0 | Command succeeded. |
general | 1 | Unexpected or uncategorized failure. |
usage | 2 | Invalid arguments or invocation. |
auth | 3 | Missing or failed authentication. |
quota | 4 | Not enough credits or quota. |
timeout | 5 | Request timed out. |
network | 6 | Network or upstream connection failure, including upstream 5xx. |
not_found | 7 | Requested resource does not exist. |
policy_blocked | 10 | Blocked by policy. |
Capabilities discovery
breeze capabilities prints a single-shot manifest of legal flag values, default endpoints, enum values, and the exit code mapping, so an agent can discover the command surface without trial and error. Pass --agent or --output json to get JSON.
Install agent skills
breeze skills install writes the Breeze agent skill bundle into a harness’s skills directory. Choose the target harness with --target: codex, claude, cursor, or all. Skills commands do not use your API key and do not call Breeze generation APIs. Use breeze skills check to report the installed skill state.
breeze update to refresh them after a CLI update:

