cd /news/ai-products/psa-claude-code-enabling-auto-mode-a… · home topics ai-products article
[ARTICLE · art-88774] src=9to5mac.com ↗ pub= topic=ai-products verified=true sentiment=· neutral

PSA: Claude Code enabling auto mode as default next week, Anthropic says

Anthropic will make auto mode the default permission setting in Claude Code starting August 14, replacing repeated approval prompts with a classifier that checks each tool call for risky actions. The company cited a study of 1,053 paid testers showing auto mode caught 89% of dangerous commands versus 13.6% for humans, and it will stop charging for the extra tokens used by the classifier. Anthropic cautions that classifiers cannot eliminate risk and recommends human review for production changes.

read2 min views1 publishedAug 7, 2026
PSA: Claude Code enabling auto mode as default next week, Anthropic says
Image: 9To5Mac (auto-discovered)

Claude Code auto mode will become the default permission setting for users next week.

Starting August 14, sessions for Pro, Max, and Team users will use it unless a user or administrator has pinned another setting.

Anthropic no longer charging for extra tokens used per tool call for auto mode classifier #

According to Anthropic, auto mode replaces repeated approval prompts with a classifier that checks each tool call for irreversible, destructive, or out-of-bounds actions.

If it blocks something, Claude can try a safer route or ask permission. After repeated blocks, the session falls back to manual approval. As part of the change, Anthropic says it will no longer charge for “small number of extra tokens per tool call” used for the auto mode classifier.

Anthropic says its study of 1,053 paid testers found people caught 13.6% of dangerous commands, compared with 89% for auto mode. Human performance fell to about 5% after 50 prompts.

Still, Anthropic cautions that classifiers cannot eliminate risk and recommends human review for production changes.

The shift should make Claude Code’s long-running work more practical, building on routines, voice mode, and its in-app Mac browser. Anthropic says auto mode users at Team and Enterprise customers ship about 25% more pull requests.

9to5Mac’s Take #

While it may sound risky, this is probably the right default for experienced users. Still, users should establish some trust with coding agents before relying on auto mode. It’s also interesting that Anthropic is taking this step. For comparison, OpenAI actually opted out of auto mode for its most powerful version of GPT-5.6 as an extra precaution at one point.

Do more with your Apple products

[Apple AirTag 2 | Add Find My tracking to keys, bags, bikes, more](https://amzn.to/4vjNWN1)

[AirPods 4 | Apple’s newest wireless headphones](https://amzn.to/43ndewV)

[AirPods Pro 3 | Apple’s best wireless headphones](https://amzn.to/4ut3FYp)

[Beats USB-A to USB-C Cable | The official CarPlay cable](https://amzn.to/4mpKs7K)

*FTC: We use income earning auto affiliate links.* [More.](https://9to5mac.com/about/#affiliate)

[our homepage](http://9to5mac.com/)for all the latest news, and follow 9to5Mac on

[exclusive stories](https://9to5mac.com/feature/exclusive/),

[reviews](https://9to5mac.com/guides/review/),

[how-tos](https://9to5mac.com/guides/how-to/), and

[subscribe to our YouTube channel](https://www.youtube.com/9to5mac)
── more in #ai-products 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/psa-claude-code-enab…] indexed:0 read:2min 2026-08-07 ·