Show HN: RepoGuards – Claude Code hooks that refuse pushes into the wrong repo

Category: devtools

Tags: ai-agents, git, claude-code, hooks, safety

Score: 6.0/10 (Innovation: 6, Technical: 6, Documentation: 7, Utility: 5)

RepoGuards is a set of Claude Code hooks that enforce safety guardrails when AI agents operate across multiple git repositories, blocking risky actions like blind commits or pushes into foreign repos and injecting context about the foreign repo's state. It also provides a session-aware commit tool and a central registry for managing skills across projects. It's an interesting, focused solution to a real emerging problem in agentic coding workflows.

Target audience: developers using AI coding agents (especially Claude Code) in multi-repo environments

Repository: https://github.com/yybd/repo-guards · Python · MIT · 2 stars

View on Hacker News