Engineering teams that let AI agents run commands and want a check against destructive actions.
git clone https://github.com/kenryu42/cc-safety-net.gitThird party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.
Loading the file...
A hook for coding agent command lines that checks what a command would do before it runs. It blocks destructive git and filesystem commands and access to secrets such as SSH keys and .env files. It is not a sandbox. It works with Claude Code, Codex, OpenCode, Gemini CLI and others.
Engineering teams that let AI agents run commands and want a check against destructive actions. A hook for coding agent command lines that checks what a command would do before it runs. It blocks destructive git and filesystem commands and access to secrets such as SSH keys and .env files. It is not a sandbox. It works with Claude Code, Codex, OpenCode, Gemini CLI and others.
Run this in your terminal: git clone https://github.com/kenryu42/cc-safety-net.git
Yes. The code is on GitHub (kenryu42/cc-safety-net) under the MIT licence.
Our automatic scan flagged points to review, so read the code before installing it. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.