yybd

Repo Guards — AI skill for Claude Code

AI community

RepoGuards — cross-repo guards for AI coding agents.

How to install Repo Guards

This entry records only its repository, not the path inside it, so there is no exact command to give. Open yybd/repo-guards and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Repo Guards does

RepoGuards — cross-repo guards for AI coding agents. Refuses a blind write or a sweeping commit into a repo the session is not standing in, and closes every place it left open. A Claude Code plugin marketplace.

Alternatives in AI

Firm — Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preser 1.3k ★
Pilotfish — Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verificati 688 ★
Cplt — Sandbox for AI coding agents 114 ★

README

*English · [עברית](README.he.md)*

RepoGuards

*Formerly Grove. Renamed in 0.2.0 — see [Upgrading from Grove](#upgrading-from-grove).*

**The safety and orchestration layer for AI agents in multi-repo environments.**

![The agent stands in my-app and reaches into app-hub: RepoGuards refuses the push and the sweeping add, shows the three commits the push would have published, and allows an exact-path add with the other repo's state attached. Real hook output on two throwaway repos.](docs/media/repoguards-demo.gif)

An AI agent (like Claude Code) is a brilliant tool when operating within a single project folder (Repository). However, in the real world, tasks cross boundaries: shipping a feature requires a code change (App), a data schema update (Hub), and editing a marketing page (Web). The moment the agent "reaches out" to a foreign directory, it loses touch with reality. Because the `git status` command is limited to its current working directory, the agent might blindly overwrite another developer's open files, push code to the wrong branch, or perform a destructive blind commit.

**RepoGuards was built to solve exactly this.** It is a set of guardrails that run inside the session, at the moment of the tool call: they detect the anomaly, refuse the two actions that cannot be undone, and hand the agent back the picture it was missing so it can correct itself.

**Built for Claude Code, and tested only there.** The guards are Claude Code hooks: they read its hook protocol and its tool names (`Bash`, `Edit`, `Write`), and `close.py` reads the journal those hooks write. The idea carries to any agent with a pre-tool hook; the code does not, yet.

The Components: What does RepoGuards do?

The system provides 3 critical solutions:

1. Active Guardrails (The Guard Hooks)

Blocking Blind Commits (scope_foreign_commits): If the AI stands in directory A and attempts to run git commit -a in directory B, the system blocks it. Instead of a generic f