CC Safety Net

English · 简体中文 · 日本語

https://github.com/user-attachments/assets/353c1441-9156-483c-b8e5-32fce7905a83

CC Safety Net (Coding CLI Safety Net) blocks destructive commands and access to secrets such as SSH keys and .env files before the tool call runs. It parses what the command does. Wrapping the command or reordering flags does not hide it. A broken config file falls back to safe defaults instead of stopping your agent. It is not a sandbox: it does not contain processes, set filesystem permissions, or watch network egress.

Full documentation → covers installation, configuration, reference material, guides, and the security model. This README is the short version.

How it works

Supported coding CLIs

CC Safety Net supports these coding agent CLIs on Windows, macOS, and Linux.

    Amp Code
    Antigravity CLI
    Claude Code
    Codex

    Cursor
    DeepSeek Harness
    Devin CLI
    Factory Droid

    Gemini CLI
    GitHub Copilot CLI
    Grok Build
    Hermes Agent

    Kimi Code
    OpenClaw
    OpenCode
    Pi

Features

- Blocks destructive commands such as git reset --hard, git push --force, and rm -rf on dangerous targets, and install scripts piped from the internet (curl … | bash), even inside bash -c or python -c. See Blocked commands.
- Blocks secret access to SSH keys, .env files, ~/.aws, and coding-CLI credentials, from the shell and from the agent's file tools. See Secret protection.
- Tunes the policy in a GUI. Run npx cc-safety-net gui to pick the Standard, Strict, or Paranoid preset and turn rules on or off. See Dashboard.
- Adds blocks through rulebooks: official packs for Terraform, AWS, gcloud, and Azure, or your own JSON. See Official rulebooks.
- Shares policy through git. Commit .cc-safety-net/ so clones and cloud sessions get the same rules. See…