guard

Enforce directory-scoped edits and destructive command warnings via Bash, Edit, and Write hooks.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/zaeem-rafiq/tatheer-swift-sdk --skill guard-zaeem-rafiq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/zaeem-rafiq/tatheer-swift-sdk/tree/main/.claude/skills/gstack/guard
Command: npx skills add https://github.com/zaeem-rafiq/tatheer-swift-sdk --skill guard-zaeem-rafiq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents unintended destructive actions and unauthorized edits by enabling a combined safety mode that surfaces destructive command warnings and enforces directory-scoped edits.

Core Features & Use Cases

  • Destructive command warnings: alerts before executing dangerous commands like rm -rf or DROP TABLE.
  • Edit boundary enforcement: restricts file edits to a specified directory to prevent accidental changes elsewhere.
  • Safe prod/debugging protection: provides guardrails during live deployments and debugging sessions to reduce risk.

Quick Start

Enable guard mode to automatically warn on destructive commands and restrict edits to a chosen directory.

Frequently Asked Questions about guard

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

FAQPage Schema
How do I prevent unintended destructive commands like rm -rf during a live production debugging session?

To prevent unintended destructive commands during production debugging, enable guard mode to surface warnings before executing dangerous Bash commands like rm -rf or DROP TABLE. This safety mode uses pre-use hooks to verify command boundaries and reduce execution risk.

Can I restrict file edits to a specific directory to avoid accidental changes elsewhere in my project?

You can restrict file edits to a specific directory by enabling edit boundary enforcement. This mode enforces directory-scoped edits, preventing unauthorized modifications to files outside the chosen project boundary.

What are pre-use hooks and how do they verify command boundaries for safe deployments?

Pre-use hooks are safety mechanisms that verify command boundaries before execution. They intercept Bash, Edit, and Write operations to enforce directory-scoped edits and alert on destructive commands, providing guardrails during live deployments.

Does this safety mode work with Bash commands and file editing hooks simultaneously?

Yes, this combined safety mode operates across Bash, Edit, and Write hooks simultaneously. It enforces directory-scoped edits and surfaces destructive command warnings together, ensuring comprehensive protection during live production or debugging sessions.

What is the best way to add guardrails for destructive actions during live deployments?

The best way to add guardrails for live deployments is enabling a combined safety mode that enforces directory-scoped edits and surfaces destructive command warnings. This approach satisfies production safety requirements by verifying command boundaries before execution.