anti-rogue-actions

Community

Prevent absurd and destructive outcomes from API calls

Authorcoff33ninja
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill prevents unauthorized, destructive, or nonsensical actions from being performed via API calls, reducing production agent failures.

Core Features & Use Cases

  • Pre-execution Sanity Checks: Ensures destructive operations are validated for permissions, bounds, and safety.
  • Bounds Enforcement: Ensures quantity, depth, scope, and limit parameters are set.
  • Dry-run Verification: Allows verification of operations before execution.
  • Scope Narrowing: Restricts operations to the smallest possible scope.
  • Confirmation for Destructive Chains: Confirms each step of a destructive chain.

Quick Start

Copy the 'sanity-check.ps1' script to your project's .ai_scripts/ directory and run it with -Command and -MaxItems flags to check for destructive commands and target size.

Dependency Matrix

Required Modules

powershell

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: anti-rogue-actions
Download link: https://github.com/coff33ninja/ai-skills-mcp/archive/main.zip#anti-rogue-actions

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.