Claude Code makes auto mode the default on Pro, Max, and Team

Anthropic said on 7 August 2026 that it is making auto mode the default in Claude Code. Starting 14 August, new sessions on Pro, Max, and Team plans run in auto mode. Users who already set a different default may get a one-time prompt. A pinned default is left alone. Anthropic also said it is no longer charging those plans for the extra classifier tokens.

Auto mode stays opt-in for now on Claude Enterprise, the Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. Anthropic said it plans to make auto mode the default there in the coming month. Enterprise admins can already set it through managed settings.

Instead of a permission prompt on every tool call, a classifier is supposed to block actions that are irreversible, destructive, or aimed outside the environment. After three blocks in a row, or twenty in a session, Claude Code falls back to manual approvals. Anthropic wrote that users approve 97% of permission prompts, and in a study of 1,053 paid testers humans caught 13.6% of planted dangerous commands while auto mode caught 89%. Among Teams and Enterprise adopters, it said auto mode users ship about 25% more pull requests. Adobe, Nuro, Gusto, and Garner Health are named as already running auto mode as a production default.

Shift+Tab in the CLI, or the mode dropdown on desktop, still switches modes. Anthropic still recommends reviewing high-stakes production changes yourself.

Source: Auto mode is now the default in Claude Code for Pro, Max, and Team plans, Anthropic, 7 August 2026.