tool-permission-system

Name: tool-permission-system
Availability: InStock
Author: simba

Enforce layered deny/allow/ask permission rules for AI agent tool calls.

132|25|Updated Mar 24, 2026

Search Tags:#workflow #hooks #ai #safety #policy #tools #permission

Ready to run

npx skills add https://github.com/simbajigege/book2skills --skill tool-permission-system

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tool-permission-system
Source: https://github.com/simbajigege/book2skills/tree/main/skills/tool-permission-system
Command: npx skills add https://github.com/simbajigege/book2skills --skill tool-permission-system

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides a layered permission pipeline to govern every tool call made by an AI agent, reducing risk and enabling configurable governance across environments.

Core Features & Use Cases

Layered rule sources (policySettings, userSettings, projectSettings, localSettings, cliArg, command, session) with a clear override order
Tool-level checkPermissions() contract and safety checks immune to bypass
Hook system and denial tracking to support enterprise-grade governance and auditable decisions
Use cases include enterprise automation, CI/CD agents, and risk-averse automation that needs configurable prompts

Quick Start

Install and configure the Tool Permission System in your agent to enforce layered deny/allow/ask decisions for every tool call.

Frequently Asked Questions about tool-permission-system

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

FAQPage Schema

How do I enforce permission controls for AI agent tool calls?▼

To enforce permission controls for AI agent tool calls, implement a layered permission pipeline that evaluates deny, allow, and ask decisions across enterprise, project, and session scopes before execution.

What is a layered rule source system for AI safety policies?▼

A layered rule source system for AI safety policies applies settings from policy, user, project, local, CLI, command, and session scopes in a clear override order to govern agent actions.

Can I use hooks to track denied tool calls in CI/CD agents?▼

Yes, you can use hooks to track denied tool calls in CI/CD agents. The system supports hook integration and denial tracking to enable enterprise-grade governance and auditable safety decisions.

How to implement safety checks immune to bypass for enterprise automation?▼

Implement safety checks immune to bypass for enterprise automation by applying a tool-level checkPermissions contract that enforces configurable governance and prompts across all agent actions.

Does the tool permission system support session-level overrides?▼

Yes, the tool permission system supports session-level overrides. It evaluates rules across multiple sources including session settings, providing a default fallback to prompting when no specific rule is found.