To configure auto mode for your environment, run /auto-mode-setup. Claude looks through your repo and suggests trusted repos and domains for you to review. The more the classifier knows about your setup, the clearer the line on what's safe to run.

Once you've configured AI with the right toolset and knowledge base, it really is unbelievable. Got pinged about Hashcats while watching Spiderman last night (Tony McGuire, none of that new bullshit). DM'd my laptop on telegram and told it to spin up a new wallet and use my PC's 3090 to run headless mining to grab some hashcats. Gave it no context but it came back a few minutes later to request funds to a new address on Robinhood and an alchemy API key. Woke up this morning to a full monitoring dashboard and a few cats in my wallet. Better than any personal assistant.

new @poteto-mode config: hardest code, judgment or vague intent: claude-fable-5-1-thinking-high hardest code, precisely specified steps: cursor-grok-4.6-xhigh-fast code, everything else: cursor-grok-4.6-xhigh-fast trivial mechanical edits: cursor-grok-4.6-xhigh-fast judgment and prose: claude-fable-5-1-thinking-high how explorer: cursor-grok-4.6-xhigh-fast how explainer: claude-fable-5-1-thinking-high how critics: claude-fable-5-1-thinking-high, cursor-grok-4.6-xhigh-fast why investigators: cursor-grok-4.6-xhigh-fast why synthesizer: claude-fable-5-1-thinking-high reflect judgment: claude-fable-5-1-thinking-high reflect tooling: cursor-grok-4.6-xhigh-fast reflect divergent: cursor-grok-4.6-xhigh-fast reflect synthesizer: claude-fable-5-1-thinking-high arena runners: claude-fable-5-1-thinking-high, cursor-grok-4.6-xhigh-fast arena cross-judge pool: claude-fable-5-1-thinking-high, cursor-grok-4.6-xhigh-fast interrogate reviewers: claude-fable-5-1-thinking-high, cursor-grok-4.6-xhigh-fast @bot helped me iterate on this based on my transcripts

btw you can configure auto mode in Claude Code in plain English the classifier is a separate model that reviews each action, so it just reads these rules when deciding what to allow/block. adding "$defaults" keeps the built-in rules as well!

Admins can now configure additional auto-mode guidance for Claude Tag. If the default permission checker classifier is blocking actions you expect Claude Tag to take, you now can attach additional rules.

Need dynamic configuration for Swift services running on Kubernetes? Swift Configuration supports hot reloading, watching specific values, and more. Learn more on the CNCF blog: