I have been bolting guardrails onto my Claude Code setup for a few months now, mostly out of self defense. The moment that did it for me was watching it run git commit --no-verify straight past a failing pre-commit check, like the check was just a friendly suggestion it could ignore. Then a week ago it got stuck retrying the same broken build command in a loop while I was away from my desk, quietly eating tokens the whole time.
So before I launch my own take on this next Tuesday, I would rather hear yours first. What is the scariest or most expensive thing your AI coding agent has actually done to a real project? And if you could give it one hard rule it could never break, what would it be?
Claude Code OS makes Claude Code behave like a disciplined senior team: it plans before coding, writes tests first, reviews its own diffs — and physically blocks secrets, `git commit --no-verify`, and force-pushes to main at the tool level. Free + MIT core; optional 52-command PRO.
DocGen AI reads your code and writes docs for you — README, API reference, and inline JSDoc comments — in 30 seconds.
Paste any code (JS, TS, Python, Go, Rust, and 10+ more languages), hit Generate, download your docs as .md files. No install, no config.
Built for devs who hate writing docs but know they should. One-time payment, lifetime access.
