Agent Email Inbox

What it does

When your agent uses it

• Building any system where email content triggers actions — AI agent inboxes
• Automated support handlers
• Email-to-task pipelines
• Any workflow processing untrusted inbound email

Example prompts

• “t mention”
• “/agent-email-inbox”

Requirements

• Python 3
• Node.js
• A credential in RESEND_API_KEY
• A credential in RESEND_WEBHOOK_SECRET

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Ask the user for their email address — You need a real email address to send test emails to. Ask the user and wait for their response…
2. 2Choose your security level — Decide how to validate incoming emails before any are processed
3. 3Set up receiving domain — Configure MX records for the user's custom domain (see Domain Setup section)
4. 4Create webhook endpoint — Handle email.received events with security built in from the start. The webhook endpoint MUST be a POST route.
5. 5Set up tunneling (local dev) — Use Tailscale Funnel (recommended) or ngrok. See references/webhook-setup.md
6. 6Create webhook via API — Use the Resend Webhook API to register your endpoint programmatically. See references/webhook-setup.md
7. 7Connect to agent — Pass validated emails to your AI agent for processing

What it can do on your machine

Read from SKILL.md and the folder at commit 71b81fa. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl
  • npm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • dns.email

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • RESEND_API_KEY
  • RESEND_WEBHOOK_SECRET

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Email Inbox loads about 4.1k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 126 tokens; SKILL.md has 1,216 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~126

When it runs · the whole SKILL.md, loaded when a task matches

~4.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~10k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:118

  nvironment file method:** Human creates `.env` file directly: `echo "RESEND_API_KEY=re_xxx" >> .env`

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Asymmetric-al/core at commit 71b81fa, republished under its MIT licence (© Asymmetric-al). 1,216 words, ~4,113 tokens.

name

agent-email-inbox

description

Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.

license

MIT

metadata.author

resend

metadata.version

3.0.4

metadata.homepage

https://resend.com/agent-skills

metadata.source

https://github.com/resend/resend-skills

references

security-levels.md, webhook-setup.md, advanced-patterns.md

Sender → Email → Resend (MX) → Webhook → Your Server → AI Agent
                                              ↓
                                    Security Validation
                                              ↓
                                    Process or Reject

const ALLOWED_SENDERS = [
  'you@youremail.com',
  'notifications@github.com',
];

async function processEmailForAgent(
  eventData: EmailReceivedEvent,
  emailContent: EmailContent
) {
  const sender = eventData.from.toLowerCase();

  if (!ALLOWED_SENDERS.some(allowed => sender === allowed.toLowerCase())) {
    console.log(`Rejected email from unauthorized sender: ${sender}`);
    await notifyOwnerOfRejectedEmail(eventData);
    return;
  }

  await agent.processEmail({
    from: eventData.from,
    subject: eventData.subject,
    body: emailContent.text || emailContent.html,
  });
}

// app/webhook/route.ts
import { Resend } from 'resend';
import { NextRequest, NextResponse } from 'next/server';

const resend = new Resend(process.env.RESEND_API_KEY);

export async function POST(req: NextRequest) {
  try {
    const payload = await req.text();

    const event = resend.webhooks.verify({
      payload,
      headers: {
        'svix-id': req.headers.get('svix-id'),
        'svix-timestamp': req.headers.get('svix-timestamp'),
        'svix-signature': req.headers.get('svix-signature'),
      },
      secret: process.env.RESEND_WEBHOOK_SECRET,
    });

    if (event.type === 'email.received') {
      // Webhook payload only includes metadata, not email body
      const { data: email } = await resend.emails.receiving.get(
        event.data.email_id
      );

      // Apply the security level chosen above
      await processEmailForAgent(event.data, email);
    }

    return new NextResponse('OK', { status: 200 });
  } catch (error) {
    console.error('Webhook error:', error);
    return new NextResponse('Error', { status: 400 });
  }
}

import express from 'express';
import { Resend } from 'resend';

const app = express();
const resend = new Resend(process.env.RESEND_API_KEY);

const ALLOWED_SENDERS = (process.env.ALLOWED_SENDERS || '').split(',').filter(Boolean);
const isAllowedSender = (sender) =>
  ALLOWED_SENDERS.some(allowed => sender === allowed.toLowerCase());

app.post('/webhook', express.raw({ type: 'application/json' }), async (req, res) => {
  try {
    const payload = req.body.toString();

    const event = resend.webhooks.verify({
      payload,
      headers: {
        'svix-id': req.headers['svix-id'],
        'svix-timestamp': req.headers['svix-timestamp'],
        'svix-signature': req.headers['svix-signature'],
      },
      secret: process.env.RESEND_WEBHOOK_SECRET,
    });

    if (event.type === 'email.received') {
      const sender = event.data.from.toLowerCase();

      if (!isAllowedSender(sender)) {
        console.log(`Rejected email from unauthorized sender: ${sender}`);
        res.status(200).send('OK'); // Return 200 even for rejected emails
        return;
      }

      const { data: email } = await resend.emails.receiving.get(event.data.email_id);
      await processEmailForAgent(event.data, email);
    }

    res.status(200).send('OK');
  } catch (error) {
    console.error('Webhook error:', error);
    res.status(400).send('Error');
  }
});

app.get('/', (req, res) => res.send('Agent Email Inbox - Ready'));
app.listen(3000, () => console.log('Webhook server running on :3000'));

import { Resend } from 'resend';

const resend = new Resend(process.env.RESEND_API_KEY);

async function sendAgentReply(to: string, subject: string, body: string, inReplyTo?: string) {
  if (!isAllowedToReply(to)) {
    throw new Error('Cannot send to this address');
  }

  const { data, error } = await resend.emails.send({
    from: 'Agent <agent@example.com>',
    to: [to],
    subject: subject.startsWith('Re:') ? subject : `Re: ${subject}`,
    text: body,
    headers: inReplyTo ? { 'In-Reply-To': inReplyTo } : undefined,
  });

  if (error) throw new Error(`Failed to send: ${error.message}`);
  return data.id;
}

# Required
RESEND_API_KEY=re_xxxxxxxxx
RESEND_WEBHOOK_SECRET=whsec_xxxxxxxxx

# Security Configuration
SECURITY_LEVEL=strict                    # strict | domain | filtered | sandboxed
ALLOWED_SENDERS=you@email.com,trusted@example.com
ALLOWED_DOMAINS=example.com
OWNER_EMAIL=you@email.com               # For security notifications

© Asymmetric-al, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in .agents/skills/agent-email-inbox of Asymmetric-al/core.

• SKILL.md
• references/advanced-patterns.md
• references/security-levels.md
• references/webhook-setup.md

Open the folder on GitHubat commit 71b81fa