● Covered by 2 sources · 2 reportsMedium impact2 neutral
Claude Code Defaults to Auto Mode for Pro, Max, and Team Plans
Key points
- Auto mode is now default for Claude Code Pro, Max, and Team plans.
- Automated classifier replaces manual approval for tool calls.
- Anthropic stopped charging for auto mode classifier tokens.
- Auto mode detected 89% of dangerous commands in testing.
- Enterprise and cloud platforms will adopt default auto mode later.
Default Auto Mode for Claude Code
Starting August 14, Claude Code will set auto mode as the default for new sessions on Pro, Max, and Team plans. This update enables longer-running autonomous work by utilizing an automated classifier to review tool calls, replacing the previous system of repeated manual approval prompts.
Users who have previously set a different default may receive a one-time prompt to switch to auto mode. Pinned defaults will remain unchanged. Anthropic has also ceased charging for the small number of extra tokens per tool call used by the auto mode classifier, effective immediately for these plans.
Improved Safety and Efficiency
Anthropic states that auto mode improves safety by catching more dangerous commands than manual review. In a study involving 1,053 paid testers, auto mode detected 89% of dangerous commands, while human testers caught 13.6%. Human performance reportedly declined to about 5% after 50 prompts.
The auto mode classifier checks each tool call for irreversible, destructive, or out-of-bounds actions. If a command is blocked, Claude can attempt a safer alternative or request permission. After multiple blocks, the session will revert to manual approval. While auto mode enhances safety, Anthropic advises that classifiers cannot eliminate all risks and recommends human review for production changes.
Broader Rollout Planned
Currently, auto mode remains an opt-in feature for Claude Enterprise, the Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. This allows administrators time to review the change before it becomes default.
Anthropic plans to make auto mode the default across all these platforms in the coming month, in collaboration with its cloud partners. The cessation of charges for classifier overhead will also extend to these platforms at that time.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
How outlets covered it
Anthropic has made auto mode the default setting for Claude Code users, which replaces repeated approval prompts with an automated classifier for tool calls. This change aims to improve efficiency for developers and Anthropic has also stopped charging for extra tokens used by the auto mode classifier.
Claude Code will set auto mode as the default for Pro, Max, and Team plans starting August 14, enabling longer autonomous operations and improved safety over manual review. This change aims to increase user productivity and will eventually extend to enterprise versions and cloud platforms.