doover

Undo for AI agent shell commands: snapshots files before destructive bash runs so agent mistakes are reversible.

Pluginfreeglobal

doover snapshots files before Claude Code runs a destructive bash command (rm -rf, git reset, rsync and similar), so an AI coding agent's mistakes are reversible even for files git never tracked. It's aimed at developers who let a coding agent run shell commands and want a safety net against destructive mistakes.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of doover - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim doover to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether doover (or something else) actually fits.

Try a problem