safety-guard

Enforce safety guards on agent actions to prevent destructive operations in production environments.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/GGEdu/claude-god-mode-template --skill safety-guard-ggedu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: safety-guard
Source: https://github.com/GGEdu/claude-god-mode-template/tree/main/skills/safety-guard
Command: npx skills add https://github.com/GGEdu/claude-god-mode-template --skill safety-guard-ggedu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents destructive operations during production work and autonomous agent execution by enforcing safe-guarding modes.

Core Features & Use Cases

  • Careful Mode intercepts destructive commands before execution and prompts for confirmation.
  • Freeze Mode locks edits to a specific directory tree to prevent unintended changes.
  • Guard Mode combines Careful and Freeze protections for maximum safety.
  • Quick unlocks and integration with common workflows to maintain productivity while reducing risk.

Quick Start

Activate safety-guard for your session and specify a protected directory to begin intercepting dangerous commands immediately.

Frequently Asked Questions about safety-guard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent destructive bash commands from executing in production?

To prevent destructive bash commands in production, activate safety-guard for your session to intercept dangerous operations and prompt for confirmation before execution.

Can I restrict autonomous agent execution to a specific directory tree?

Yes, you can restrict autonomous agent execution to a specific directory tree by enabling Freeze Mode, which locks edits to prevent unintended changes outside the protected path.

What is the difference between careful, freeze, and guard modes?

Careful Mode intercepts destructive commands for confirmation, Freeze Mode locks edits to a directory tree, and Guard Mode combines both protections for maximum safety during sensitive migrations.

How do I maintain workflow productivity while blocking dangerous deployments?

You maintain workflow productivity while blocking dangerous deployments by using safety-guard's quick unlocks and integration options, which reduce risk without halting authorized sensitive migrations.

Does safety-guard work for sensitive migrations and restricted directory work?

Yes, safety-guard works for sensitive migrations and restricted directory work by enforcing safety guards on agent actions, offering careful, freeze, and guard modes to prevent unintended destructive operations.