← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

destructive_command_guard

github.com

A fast Rust safety hook that blocks destructive shell, git, and filesystem commands before AI coding agents run them. 50+ security packs (databases, Kubernetes, Docker, cloud, Terraform), heredoc/inline-script scanning, CI scan mode, and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor, and more.

CLIOpen source

Visit github.comexternal siteGitHub6,290 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. A pre-execution guard that stops AI agents running destructive commands

    A pre-execution guard that stops your coding agent running destructive commands. One shell file, no dependencies.

    github.comOpen source2 reactionslatest reaction

    Hacker News
    5 pts
    GitHub
    3 stars

  2. A Claude Code plugin that catch destructive Git and filesystem commands

    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.

    github.comCLIOpen source2 reactionslatest reaction

    Hacker News
    61 pts
    GitHub
    1,947 stars

  3. A context-aware permission guard for Claude Code

    a guard that blocks catastrophic agent actions

    github.comOpen source2 reactionslatest reaction

    Hacker News
    127 pts
    GitHub
    494 stars

  4. gotatun

    Userspace WireGuard® Implementation in Rust

    github.comOpen sourcelatest reaction

    Hacker News
    No reaction
    GitHub
    1,396 stars

  5. I built a Rust crate for running unsafe code safely

    A Rust crate for containing memory leaks and fragmentation

    github.comOpen source2 reactionslatest reaction

    Hacker News
    113 pts
    GitHub
    250 stars