mthwsjc_Mar 29

Claude Code runs Git reset –hard origin/main against project repo every 10 mins

https://github.com/anthropics/claude-code/issues/40710

Claude is running git reset --hard origin/main in my project every 10 minutes · Issue #40710 · anthropics/claude-code

Update (2026-03-30): Root cause identified — this was NOT a Claude Code bug. The resets were caused by a separate tool I built that was running locally, which used GitPython to hard-reset the worki...

GitHub
Show threadsimianwordsMar 30
I think this post potentially mischaracterises what may be a one off issue for a certain person as if it were a broader problem. I'm guessing some context has been corrupted?
Show threadjeswinMar 30

It's not a one off issue - it has happened to me a few times. It has once even force pushed to github, which doesn't allow branch protection for private personal projects. Here's an example.

1) claude will stash (despite clear instructions never to do so).

2) claude will use sed to bulk replace (despite clear instructions never to do so). sed replacements make a mess and replaces far too many files.

3) claude restores the stash. Finds a lot of conflicts. Nothing runs.

4) claude decides it can't fix the problem and does a reset hard.

I have this right at the top of my CLAUDE.md and it makes things better, but unlike codex, claude doesn't follow it to the letter. However, it has become a lot better now.

NEVER USE sed TO BULK REPLACE.

*NEVER USE FORCE PUSH OR DESTRUCTIVE GIT OPERATIONS*: `git push --force`, `git push --force-with-lease`, `git reset --hard`, `git clean -fd`, or any other destructive git operations are ABSOLUTELY FORBIDDEN. Use `git revert` to undo changes instead.

Show threadunchar1
Claude tends to disregard "NEVER do X" quite often, but funnily enough, if you tell it "Always ask me to confirm before going X", it never fails to ask you. And you can deny it every time
Mar 30 at 1:30amWeb
Show threadSoftTalkerMar 30
If it disregards "NEVER do" instructions, why would it honor your denial when it asks?
Show threadjacheeMar 30
Because it’s just fancy auto-complete.
Show threadZetaphorMar 30

There are plenty of examples in the RL training showing it how and when to prompt the human for help or additional information. This is even a common tool in the "plan" mode of many harnesses.

Conversely, it's much harder to represent a lack of doing something