guard

Warn before destructive commands and restrict edits to a specified directory.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/pistosmin/base-one --skill guard-pistosmin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/pistosmin/base-one/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/pistosmin/base-one --skill guard-pistosmin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety".

Core Features & Use Cases

  • Destructive command warnings: prompts before executing dangerous commands.
  • Directory-bound edits: enforces edit restrictions to a defined path.
  • Safe-setup workflow: relies on sibling /careful and /freeze hooks to enforce safety at run time.

Quick Start

Enable guard mode to activate both destructive command warnings and edit boundaries.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I prevent accidental destructive commands like rm -rf or force-push during production debugging?

Preventing accidental destructive commands requires enabling safety gates that warn before executing dangerous operations. Guard mode activates pre-tool hooks to intercept and prompt confirmation for actions like rm -rf, DROP TABLE, or force-push during maintenance and live debugging sessions.

Can I restrict edits to a specific directory during incident response?

Yes, you can restrict edits to a specific directory by implementing freeze boundaries. Guard mode enforces directory-scoped edit restrictions, blocking any unauthorized modifications outside a defined path during critical incident response or debugging workflows.

What is full safety mode for live system debugging and how does it work?

Full safety mode for live system debugging combines destructive command warnings with directory-bound edit restrictions. It integrates pre-tool hooks invoking sibling careful and freeze scripts to enforce safety boundaries before any tool executes, ensuring strict change control.

Does guard mode require sibling scripts to enforce change control over critical directories?

Yes, guard mode requires sibling careful and freeze scripts to enforce change control over critical directories. It relies on these pre-tool hooks to intercept destructive commands and apply directory-scoped edit restrictions at run time during production maintenance.

What is the best way to lock down a production environment for maximum safety during maintenance?

The best way to lock down a production environment for maximum safety is activating guard mode. It combines destructive command warnings with directory-scoped edit restrictions, utilizing pre-tool hooks to enforce strict safety boundaries during maintenance and debugging.