Anthropic adds permissions auto mode in Claude Code

https://ift.tt/ABxsWnr

Anthropic today introduced a new permissions auto mode in Claude Code that allows Claude to make permission decisions on your behalf, with safeguards monitoring actions before they run.

In Claude Code, default permissions need human approval, for safety, yet some developers skip those permissions, which could lead to what Antrophic called “dangerous and destructive outcomes.” Auto mode enables users to run longer tasks with fewer check-ins, which provides more safety than skipping all permissions. According to the company announcement, “before each tool call runs, a classifier reviews it to check for potentially destructive actions like mass deleting files, sensitive data exfiltration, or malicious code execution.” So, actions move forward if deemed safe by the classifier, while those deemed risky are blocked. Only if Claude actions are repeatedly blocked does a permission prompt get sent to the user. The company noted that some risky actions might still be allowed by the classifier, such as when user intent is ambiguous, or the Claude lacks context around your environment to know an action might bring risk. This is why it recommends using it only in isolated environments.

Auto mode, Anthropic said, may have a small impact on token consumption, cost, and latency for tool calls.

Getting started

Auto mode is available in Claude Code as a research preview for Claude Team users today, and will roll out to Enterprise and API users in the coming days. It works with both Claude Sonnet 4.6 and Opus 4.6.

• For admins: Auto mode will soon be available for all Claude Code users on Enterprise, Team, and Claude API plans. To disable it for the CLI and VS Code extension, set “disableAutoMode”: “disable” in your managed settings. Auto mode is disabled by default on the Claude desktop app, and can be toggled on using Organization Settings -> Claude Code.
• For developers: Run `claude –enable-auto-mode` to enable auto mode, then cycle to it with Shift+Tab. On Desktop and in the VS Code extension, first toggle auto mode on in Settings -> Claude Code, then select it from the permission mode drop-down in a session.

Explore the docs for more information.

“Auto mode is another milestone from the Claude Code team shipping for the future of AI-powered coding – and the reality of these workflows,” the company wrote in a blog announcement. “The launch comes off the back of Claude Code Review, Dispatch for Cowork, and an expansion of the 1M context window, all launched in the last month.”

The post Anthropic adds permissions auto mode in Claude Code appeared first on SD Times.

Tech Developers