[0x_rs]

>Thanks for the report! This was an overactive anti-abuse system. Fixed.

This is the most interesting line to me. "Anti-abuse system"? I would bet the system is far from being just a conditional on a specific filename. In other words, this supposed anti-abuse system might be far more pervasive without the user's knowledge. And perhaps even more importantly, who thought upcharging instead of blocking is the correct approach to dealing with this alleged "abuse"? Is this some anti-distillation feature they let Claude itself write looking at past distillation attempts producing similar artifacts or what?

[AlotOfReading]

If I had to guess, this is a continuation of Anthropic's ongoing war to make third party tool usage go through per-token billing, specifically against a tool called Hermes-agent [0]. You can easily imagine why Anthropic might want to silently re-bill a customer violating their silly ToS restrictions and how an LLM told to implement the feature might arrive at this "solution".

[0] https://github.com/NousResearch/hermes-agent

[InvidFlower]

As the other person mentioned, they have said they are restricting third-party agent systems like OpenClaw and Hermes from using the monthly plan. But yeah, this seems like the wrong way to handle it, trying to detect those other harnesses via clues, and auto-changing billing. Instead, seems like it'd be better to allows vs block, like require some special encrypted signature system or similar that only Claude Code and their desktop app implement. Any other requests just get immediately blocked. Then there's a separate key for normal pay-by-the-token usage that is just unrestricted. Would make things waaaay clearer.