guard

Warn before executing destructive commands within a project directory.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill prevents accidental destructive changes by warning before executing dangerous commands.

Core Features & Use Cases

  • Destructive command warnings: prompts before rm -rf, DROP TABLE, force-push, etc.
  • Directory-bound editing: blocks edits outside a user-specified directory.
  • Safe collaboration: ensures team code changes stay within approved scopes for audits.

Quick Start

Activate guard mode by enabling both careful and freeze protections for your targeted project directory.

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 bash commands during prod debugging?

To prevent accidental destructive bash commands, this Skill warns before executing dangerous operations like `rm -rf` or `DROP TABLE` and enforces a directory-bound edit boundary to keep changes scoped safely.

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

Yes, you can restrict shell edits to a specific project directory; this Skill enforces a directory-bound boundary that blocks any modifications outside your user-sified scope during maintenance.

How does warning before force-push and destructive commands work?

Warning before force-push and destructive commands works by intercepting risky shell operations and prompting for confirmation, integrating with sibling careful and freeze guards to ensure maximum safety.

What is the best way to enforce safe collaboration boundaries for routine server management?

The best way to enforce safe collaboration boundaries is activating this Skill's directory-bound protection, which ensures team code changes stay within approved scopes for audits and blocks out-of-scope edits.

Do I need to enable careful and freeze guards to use directory-bound protection?

Yes, you need to enable both careful and freeze protections to fully activate guard mode, integrating multiple safety layers to prevent accidental destructive changes in your targeted project directory.

What destructive commands does this safety guard intercept?

This safety guard intercepts destructive commands including `rm -rf`, `DROP TABLE`, and force-push operations, warning before execution to prevent accidental data loss during deployments or server management.