guard

Block destructive commands and restrict edits to a specified directory.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/curielmc/beat-SPY --skill guard-curielmc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/curielmc/beat-SPY/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/curielmc/beat-SPY --skill guard-curielmc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Activates both destructive command warnings and directory-scoped edit restrictions, combining two safety mechanisms for high-risk operations.

Core Features & Use Cases

  • Destructive command warnings for rm -rf, DROP TABLE, force-push, and other dangerous actions.
  • Edit boundary enforcement that restricts edits to a user-specified directory.
  • Safe, predictable protection during prod maintenance and debugging of live systems.

Quick Start

Ask the user which directory to restrict edits to and enable both safeguards.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I block destructive commands like rm -rf and DROP TABLE during live-system debugging?

To block destructive commands during live-system debugging, you enable destructive command warnings that intercept risky actions like rm -rf and DROP TABLE before execution. This prevents accidental data loss in high-risk environments.

Can I restrict file edits to a specific directory during prod maintenance?

Yes, you can restrict file edits to a specific directory during prod maintenance by enforcing a per-directory edit boundary. This containment ensures changes do not impact files outside the designated scope.

What is the best way to enforce edit boundaries and command warnings for incident-response workflows?

The best way to enforce edit boundaries and command warnings for incident-response workflows is to combine directory-scoped restrictions with destructive command interception. This dual safety mechanism ensures changes remain contained and predictable.

Do I need specific dependencies installed to enable edit boundaries and command warnings?

You need the /careful and /freeze components installed alongside the skill to enable edit boundaries and command warnings. These components provide the necessary guardrails for full safety mode.

How do I set up directory-scoped edit restrictions for high-risk operations?

To set up directory-scoped edit restrictions for high-risk operations, specify the target directory to restrict edits to and enable the safety mode. This confines all modifications strictly to the chosen boundary.