> But the current models are capable of being trained in a way to steer agentic behavior from reasoned token generation.

This does not appear to be sufficient in the current state, as described in the project's README.md:

  Why This Exists

  We learned the hard way that instructions aren't enough to 
  keep AI agents in check. After Claude Code silently wiped 
  out hours of progress with a single rm -rf ~/ or git 
  checkout --, it became evident that "soft" rules in an 
  CLAUDE.md or AGENTS.md file cannot replace hard technical 
  constraints. The current approach is to use a dedicated 
  hook to programmatically prevent agents from running 
  destructive commands.

I wasn’t able to get my point across. But I completely agree