Skills
.Work. You
Rest

agent-access-control

Community

Control who can reach your AI agent.

Software Engineering#messaging#rate limiting#access control#audit logging#approval workflow#identity matching
AuthorLudwigAJ
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps you protect an AI agent from unknown or unwanted contacts by defining clear access tiers, owner approval flows, and safe default behavior for strangers.

Core Features & Use Cases

  • Tiered permissions: Separate owners, trusted contacts, chat-only users, and blocked senders with different capabilities.
  • Stranger deflection and approval: Send a diplomatic first response, notify the owner, and let the owner approve, restrict, or block the contact.
  • Multi-platform handling: Normalize IDs and enforce the same policy across WhatsApp, Telegram, Discord, Signal, and similar messaging channels.
  • Safety controls: Apply per-tier rate limits, audit logging, and strict tool restrictions to reduce abuse and protect private data.

Quick Start

Ask the Skill to set up a memory-backed access-control policy for your AI agent, including owner IDs, stranger messaging, approval handling, and rate limits.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: agent-access-control
Download link: https://github.com/LudwigAJ/swell/archive/main.zip#agent-access-control

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 537,000+ vetted skills library on demand.