Claude Code leak suggests Anthropic is working on a 'Proactive' mode for its coding tool

What should have been a routine release has revealed some of the features Anthropic has been working on for Claude Code. As reported by Ars Technica, The Verge and others, after the company released Claude Code's 2.1.88 update on Tuesday, users found it contained a file that exposed the app's source code. Before Anthropic took action to plug the leak, the codebase was uploaded to a public GitHub repository, where it was subsequently copied more than 50,000 times. All told, the entire internet (and Anthropic's competitors) got a chance to examine more than 512,000 lines of code and 2,000 TypeScript files. In the aftermath, some people claim to have found evidence of upcoming features Anthropic is working to develop. Over on X, Alex Finn, the founder of AI startup Creator Buddy, says he found a flag for a feature called Proactive mode that will see Claude Code work even when the user hasn't prompted it to do something. Finn claims he also found evidence of a crypto-b