skills.rest
kitfunso
kitfunsoCOMMUNITY
Explore all skills by this author →
Website𝕏@keithso27GitHub

guard

Enforce destructive-command warnings and directory-boundary policies during tool usage.

Updated Apr 9, 2026
Search Tags:#automation#production#safety#risk-mitigation#destructive-warnings#edit-boundary#guard-mode
One-click install
npx skills add https://github.com/kitfunso/omniskill --skill guard-kitfunso
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: guard
Source: https://github.com/kitfunso/omniskill/tree/main/skills/guard
Command: npx skills add https://github.com/kitfunso/omniskill --skill guard-kitfunso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Full safety mode prevents accidental destructive edits by enforcing warnings and restricting edits to a user-specified directory, reducing risk during critical work.

Core Features & Use Cases

  • destructive-command warnings before potentially dangerous actions (rm -rf, DROP TABLE, force-push, etc.)
  • directory-boundary enforcement that blocks edits outside a chosen path
  • cross-skill coordination with /careful and /freeze for integrated safety in prod debugging

Quick Start

Enable guard mode by selecting a restricted directory and enabling destructive-command warnings.

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 during production debugging?▼

To prevent accidental destructive commands during production debugging, you need a safety mode that enforces warnings before executing risky actions. This skill blocks dangerous operations by intercepting commands and prompting the user for explicit confirmation.

How does directory-boundary enforcement work for restricting file edits?▼

Directory-boundary enforcement works by restricting all file modifications to a user-specified safe path. It blocks any automated edits attempted outside the chosen directory, ensuring controlled changes are confined to a safe boundary.

Can I use safety orchestration to block force-push and DROP TABLE commands?▼

Yes, you can use safety orchestration to block force-push and DROP TABLE commands. The system enforces destructive-command warnings by running pre-checks that identify risky actions and prompt the user before execution proceeds.

What is the best way to enforce edit boundaries for sensitive deployments?▼

The best way to enforce edit boundaries for sensitive deployments is integrating pre-checks and boundary enforcement into your workflow. This approach restricts edits to a chosen directory and triggers warnings for risky commands, mitigating production risk.

Does this safety mode coordinate with other tools for production safety?▼

Yes, this safety mode coordinates cross-skill with other tools like /careful and /freeze. This integration provides comprehensive safety orchestration during live system debugging by combining boundary enforcement with broader risk-mitigation protocols.

Related Skills

Explore More Software Engineering Skills→
agentic-inagentic-in
577

Inference

Select inference paths, serving stacks, and benchmarking plans for ML models.

Official
Intermediate
tamaguitamagui
14.1k

git-safety

Enforce safe Git operations by blocking destructive commands during push, reset, and cleanup workflows.

Official
Basic
onlypfachionlypfachi

guard

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

Community
Advanced
ekrishguptaekrishgupta
1

guard

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

Community
Advanced