Opus 4.7 loves doing complex, long-running tasks: deep research, refactoring code, building complex features, iterating until a performance benchmark is hit. In the past, you either had to babyset the model while it did these sorts of long tasks, or use --dangerously-skip-permissions.
Anthropic recently rolled out auto mode as a safer alternative. In this mode, permission prompts are routed to a model-based classifier that decides whether the command is safe to run:
- If it's safe, auto-approve
- If it's risky, pause and ask
This means no more babysitting while the model runs. More than that, it means you can run more Claudes in parallel — if safe, you can switch focus to the next Claude.
Auto mode is now available for Opus 4.7 for Max, Teams, and Enterprise users. Shift+Tab to cycle between Ask permissions → Plan mode → Auto mode in the CLI, or choose it from the dropdown in Desktop or VS Code.