#300 · Primary category： AI Coding Assistants
cc-safety-net
An AI coding agent guardrail — a CLI hook that blocks destructive git and filesystem commands and secret file access before they execute. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Copilot CLI, Cursor, Gemini CLI, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
Project last updated：08/29/26
GitHub Stars
1.5K
Forks
75
Contributors
6
License
MIT
Why we included this project
A coding agent will happily run any shell command in your repository, and one misread instruction can end in rm -rf on your home directory or a destructive git checkout. CC Safety Net intercepts those commands as a PreToolUse hook, parsing what the command actually means rather than matching keywords, so reordered flags, shell wrappers, and interpreter one-liners don't get past it. It blocks destructive git and filesystem operations plus access to secret files, and it supports a long list of agents including Claude Code, Codex, Gemini CLI, Copilot CLI, Cursor, and others. If you run agents with any degree of autonomy, this gives you a hard technical backstop that the soft rules in CLAUDE.md can't provide, and it stops the command before anything executes.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.