explaingit

patrickjs/destructive_command_guard

Analysis updated 2026-07-18 · repo last pushed 2026-05-11

Audience · developerComplexity · 1/5MaintainedSetup · easy

TLDR

A safety tool that intercepts dangerous commands from AI coding agents like Claude Code or Copilot before they run, blocking things like accidental git resets or rm -rf.

Mindmap

mindmap
  root((dcg))
    What it does
      Blocks destructive commands
      Explains the danger
      Suggests safer options
    Works with
      Claude Code
      GitHub Copilot
      Cursor and Gemini CLI
    Protection
      Risky git operations
      Filesystem deletions
      Database deletions
    Extras
      Security packs
      One time bypass
      CI scan mode

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Stop an AI coding agent from accidentally running git reset --hard or rm -rf and wiping out your work.

USE CASE 2

Add extra security packs to guard stack-specific tools like PostgreSQL, Docker, Kubernetes, or Terraform.

USE CASE 3

Run dcg's scan mode in a CI/CD pipeline to catch dangerous command patterns during code review.

What is it built with?

Shellcurl

How does it compare?

patrickjs/destructive_command_guard0verflowme/alarm-clock0verflowme/seclists
Language—CSS—
Last pushed2026-05-112022-10-032020-05-03
MaintenanceMaintainedDormantDormant
Setup difficultyeasyeasyeasy
Complexity1/52/51/5
Audiencedevelopervibe coderops devops

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

Fail-open design, if dcg itself breaks, your commands still go through instead of locking you out.

Copy-paste prompts

Prompt 1
Show me the single curl command to install destructive_command_guard so it protects my AI coding agent.
Prompt 2
Help me add a one-time bypass in dcg for a destructive command I actually need to run right now.
Prompt 3
Explain how dcg tells the difference between searching for 'rm -rf' in code versus actually executing it.
Prompt 4
Walk me through enabling dcg's Docker and Kubernetes security packs for my stack.

Frequently asked questions

What is destructive_command_guard?

A safety tool that intercepts dangerous commands from AI coding agents like Claude Code or Copilot before they run, blocking things like accidental git resets or rm -rf.

Is destructive_command_guard actively maintained?

Maintained — commit in last 6 months (last push 2026-05-11).

How hard is destructive_command_guard to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is destructive_command_guard for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.

Alternatives & similar repos