Agent Email Inbox

This is Resend's official skill for building email-triggered workflows with actual security patterns baked in. If you're building an AI agent inbox, support ticketing system, or anything that lets untrusted emails trigger code execution, start here. The skill enforces webhook-based receiving (no polling), includes sender allowlists and domain filtering, and covers the DNS setup for custom domains. It defaults to strict security levels because the alternative is letting random internet strangers send commands to your agent. The documentation includes SDK version requirements across eight languages and proper webhook verification patterns. Use this anytime email becomes an input channel, not just for "agent" use cases.

skills.sh installs: 13.9K
GitHub stars: 211
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add resend/resend-skills --skill agent-email-inbox --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Agent Email Inbox

Overview

This skill covers setting up a secure email inbox that allows your application or AI agent to receive and respond to emails, with content safety measures in place.

Core principle: An AI agent's inbox receives untrusted input. Security configuration is important to handle this safely.

The skill builds the agent on a Resend Inbox. An inbox groups email into threads, and your agent replies inside the thread with one call. Resend sets the recipients and the threading headers. If the user has no custom domain, or their plan has no inbox available, use Receiving without an inbox instead. The security levels are the same for both.