@bcherny: The team and I use Auto mode exclusively, and have been for many months. I couldn't imagine going back to permission pr…
Summary
Claude Code will make auto mode the default permission mode for Pro, Max, and Team users starting August 14. Auto mode's separate classifier caught 89% of dangerous commands in testing, compared to 14% for manual approval.
View Cached Full Text
Cached at: 08/07/26, 08:56 PM
The team and I use Auto mode exclusively, and have been for many months. I couldn’t imagine going back to permission prompts! Really excited to get this out to everyone.
ClaudeDevs (@ClaudeDevs): Starting August 14, auto mode will be the default permission mode in Claude Code for Pro, Max, and Team users.
Auto mode reviews shell commands and actions with a separate classifier. In testing, it caught 89% of dangerous commands. Manual approval caught 14%.
Similar Articles
Auto mode is now the default in Claude Code for Pro, Max, and Team plans
Anthropic is making auto mode the default in Claude Code for Pro, Max, and Team plans starting August 14, backed by evals claiming auto mode blocks 89% of harmful actions and resists all tested indirect prompt injection attacks.
Claude Code auto mode: a safer way to skip permissions
Anthropic introduces 'auto mode' for Claude Code, a feature that uses model-based classifiers to automate permission approvals, aiming to reduce user fatigue while maintaining security against unsafe actions.
Anthropic is turning Claude Code’s auto mode on by default
Anthropic is making Claude Code's auto mode the default for Pro, Max, and Team accounts starting August 14, reducing the need for manual approval prompts while adding safety features like prompt injection screening and hard deny rules.
Auto mode is now the default in Claude Code
Anthropic is making auto mode the default in Claude Code for Pro, Max, and Team plans, citing safety research and productivity gains, with classifier overhead now free for those plans.
@FinanceYF5: 官方博客：
Anthropic is making auto mode the default in Claude Code for Pro, Max, and Team plans, balancing uninterrupted autonomy with a safety classifier that blocks risky actions. Safety data and customer results show auto mode matches or outperforms manual review, unlocking longer autonomous runs and ~25% more PRs shipped.