Rea
Reverse engineer anything with agents, from app behavior down to native binaries.
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
<h1> <picture> <source media="(prefers-color-scheme: dark)" srcset="./.github/assets/cc-safety-net-header-logo-dark.svg"> <source media="(prefers-color-scheme: light)" srcset="./.github/assets/cc-safety-net-header-logo-light.svg"> <img alt="CC Safety Net" src="./.github/assets/cc-safety-net-header-logo-light.svg"> </picture> </h1> [](https://github.com/kenryu42/cc-safety-net/actions/workflows/ci.yml)
git clone --depth 1 https://github.com/kenryu42/cc-safety-net.git ~/.claude/skills/cc-safety-net
Restart Claude Code afterwards. See the README for skill-specific setup.
Using Codex CLI? Copy the same folder to ~/.codex/skills/cc-safety-net instead.
No specific triggers listed.
<h1> <picture> <source media="(prefers-color-scheme: dark)" srcset="./.github/assets/cc-safety-net-header-logo-dark.svg"> <source media="(prefers-color-scheme: light)" srcset="./.github/assets/cc-safety-net-header-logo-light.svg"> <img alt="CC Safety Net" src="./.github/assets/cc-safety-net-header-logo-light.svg"> </picture> </h1> [](https://github.com/kenryu42/cc-safety-net/actions/workflows/ci.yml)
Clone it into your personal skills folder: git clone --depth 1 https://github.com/kenryu42/cc-safety-net.git ~/.claude/skills/cc-safety-net — then restart Claude Code.
Cc Safety Net is open source on GitHub (2078 stars at last check) and published by kenryu42.
Browse other security skills in the Security category of this directory.