Agent skill

Agent Email Inbox

by viclafouch in viclafouch/meme-studio

A skill your agent uses when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing…

No licenceAuto-check: warningsBackend & APIs

Install Agent Email Inbox

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add viclafouch/meme-studio --skill agent-email-inbox -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install viclafouch/meme-studio agent-email-inbox --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/viclafouch/meme-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/resend/agent-email-inbox .claude/skills/agent-email-inbox && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-email-inbox
GitHub stars
110
Used in
2 other repos
Token cost
~10k tokens
SKILL.md length
3,138 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing…

  • Works in 2 steps: Set up tunneling to get a stable public… → Choose your webhook path and NEVER…
  • Setting up an email inbox for an AI agent (Moltbot
  • SKILL.md covers Overview, Architecture, SDK Version Requirements and Quick Start, plus 5 more sections
  • Calls ngrok, cloudflared and npm; reaches a1b2c3d4.ngrok-free.app and api.resend.com; needs RESEND_API_KEY and RESEND_WEBHOOK_SECRET

What it does

Agent Email Inbox is an agent skill from viclafouch/meme-studio. Use when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks.

Its SKILL.md is about 10k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Email management, Webhooks and Prompt injection and agent security. It works with React. The repository describes itself as: 📌 A complete and fast website building in Next.js for creating and sharing "internet memes".

When your agent uses it

  • Setting up an email inbox for an AI agent (Moltbot
  • Similar) - configuring inbound email
  • Tunneling for local development
  • Implementing security measures to prevent prompt injection attacks

Example prompts

  • “/agent-email-inbox”

Requirements

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

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Set up tunneling to get a stable public URL
  2. Choose your webhook path and NEVER change it

What it can do on your machine

Read from SKILL.md and the folder at commit d8fa0be. 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:

    • ngrok
    • cloudflared
    • npm
    • curl
    • brew
    • npx
    • vercel

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • a1b2c3d4.ngrok-free.app
    • api.resend.com
    • owasp.org
    • ngrok.com

    Also links to:

    • 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 10k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 3,138 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~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

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • NoteMentions a .env fileSKILL.md:86
    - Human creates `.env` file directly: `echo "RESEND_API_KEY=re_xxx" >> .env`
  • WarningMentions a paste, webhook or tunnelling service often used to send data outSKILL.md:474
    ngrok http --domain=myagent.ngrok.io 3000
  • WarningMentions a paste, webhook or tunnelling service often used to send data outSKILL.md:477
    generated URL (e.g., `https://a1b2c3d4.ngrok-free.app`). You'll register this with Resend shortly.
  • NoteMentions a .env fileSKILL.md:646
    // Write it directly to .env, never log it
  • NoteMentions a .env fileSKILL.md:647
    // fs.appendFileSync('.env', `\nRESEND_WEBHOOK_SECRET=${data.signing_secret}\n`);
  • NoteMentions a .env fileSKILL.md:663
    # Write the signing secret directly to .env, never log it
  • NoteMentions a .env fileSKILL.md:664
    # with open('.env', 'a') as f:
  • WarningMentions a paste, webhook or tunnelling service often used to send data outSKILL.md:742
    every restart (e.g., `https://a1b2c3d4.ngrok-free.app`)
  • WarningMentions a paste, webhook or tunnelling service often used to send data outSKILL.md:747
    across restarts (e.g., `https://myagent.ngrok.io`)
  • WarningMentions a paste, webhook or tunnelling service often used to send data outSKILL.md:763
    ngrok http --domain=myagent.ngrok.io 3000

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 3,138 words (~10,258 tokens).

“Moltbot (formerly Clawdbot) is an AI agent that can send and receive emails. This skill covers setting up a secure email inbox that allows your agent to be notified of incoming emails and respond appropriately, while protecting against prompt injection…”

— opening of SKILL.md by viclafouch
name
agent-email-inbox

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/resend/agent-email-inbox of viclafouch/meme-studio.

Open the folder on GitHubat commit d8fa0be

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in viclafouch/meme-studio, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Agent Email Inbox next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Email Inbox compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Email Inbox this skillviclafouch/meme-studio1102 repos~10kAutomated safety check: WarnNone
Email Connectorericrisco/rsc-harness180—~3.1kAutomated safety check: PassMIT
Aqua Communicationquailyquaily/aqua258—~4.7kAutomated safety check: NotesApache-2.0
Agentmailsundial-org/awesome-openclaw-skills6631 repos~1.5kAutomated safety check: WarnNone
Stripe Appsfossasia/eventyay1.7k1 repos~3.6kAutomated safety check: PassApache-2.0
Watcher Creatorasheshgoplani/agent-deck1.1k—~2.7kAutomated safety check: PassMIT

Similar skills

  • Email Connector

    ericrisco/rsc-harness

    A skill your agent uses when wiring server code to send transactional or bulk email via Resend, SendGrid, or Postmark: a provider-agnostic sendEmail() seam, idempotent retries, 100-cap batches with…

    180 GitHub stars~3.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Aqua Communication

    quailyquaily/aqua

    Aqua is a CLI-first message tool for AI agents. An agent skill from quailyquaily/aqua.

    258 GitHub stars~4.7k tokensUpdated 6 mo ago
    Backend & APIsAuto-check: notes
  • Agentmail

    sundial-org/awesome-openclaw-skills

    API-first email platform designed for AI agents. An agent skill from sundial-org/awesome-openclaw-skills.

    663 GitHub starsUsed in 1 repo~1.5k tokens
    Backend & APIsAuto-check: warnings
  • Stripe Apps

    fossasia/eventyay

    A skill your agent uses when building, modifying, or reviewing a Stripe App — or when the user describes something that implies one (e.g.

    1.7k GitHub starsUsed in 1 repo~3.6k tokens
    Backend & APIsAuto-check passed
  • Watcher Creator

    asheshgoplani/agent-deck

    Guide for creating agent-deck watchers conversationally. An agent skill from asheshgoplani/agent-deck.

    1.1k GitHub stars~2.7k tokensUpdated today
    Backend & APIsAuto-check passed
  • E2a Doctor

    tokencanopy/e2a

    A skill your agent uses when an existing e2a MCP connection, inbox, custom domain, protection policy, webhook, or message delivery is failing or unclear.

    193 GitHub stars~994 tokensUpdated 4 days ago
    Backend & APIsAuto-check passed

More from viclafouch/meme-studio

All 12 skills in this repo
  • Email Best Practices

    viclafouch/meme-studio

    A skill your agent uses when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM…

    110 GitHub starsUsed in 7 repos~787 tokens
    Auto-check passed
  • React Email

    viclafouch/meme-studio

    A skill your agent uses when creating HTML email templates with React components - welcome emails, password resets, notifications, order confirmations, newsletters, or transactional emails.

    110 GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed
  • Send Email

    viclafouch/meme-studio

    A skill your agent uses when sending transactional emails (welcome messages, order confirmations, password resets, receipts), notifications, or bulk emails via Resend API.

    110 GitHub starsUsed in 2 repos~3.8k tokens
    Auto-check passed
  • Resend

    viclafouch/meme-studio

    A skill your agent uses when working with Resend email platform - routes to specific sub-skills for sending, receiving, audiences, or broadcasts.

    110 GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed
  • Better Auth Best Practices

    viclafouch/meme-studio

    Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.

    110 GitHub starsUsed in 5 repos~1.5k tokens
    Auto-check passed
  • Resend Inbound

    viclafouch/meme-studio

    A skill your agent uses when receiving emails with Resend - setting up inbound domains, processing email.received webhooks, retrieving email content/attachments, or forwarding received emails.

    110 GitHub starsUsed in 2 repos~2.1k tokens
    Auto-check: warnings

Works with

Questions about Agent Email Inbox

What does Agent Email Inbox do?

A skill your agent uses when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing…. Agent Email Inbox is an agent skill from viclafouch/meme-studio. Use when setting up an email inbox for an AI agent (Moltbot, Clawdbot, or similar) - configuring inbound email, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks.

When should I use Agent Email Inbox?

Agent Email Inbox fits situations like: setting up an email inbox for an AI agent (Moltbot; similar) - configuring inbound email; tunneling for local development; implementing security measures to prevent prompt injection attacks.

How do I install Agent Email Inbox in Claude Code?

Run `npx skills add viclafouch/meme-studio --skill agent-email-inbox -a claude-code`. Or copy the skill folder (.agents/skills/resend/agent-email-inbox in viclafouch/meme-studio) into .claude/skills/agent-email-inbox in your project. Claude Code loads it when a task matches its description.

How do I install Agent Email Inbox in Codex?

Run `npx skills add viclafouch/meme-studio --skill agent-email-inbox -a codex`. Or copy the skill folder (.agents/skills/resend/agent-email-inbox in viclafouch/meme-studio) into .agents/skills/agent-email-inbox in your project. Codex loads it when a task matches its description.

Can I use Agent Email Inbox in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add viclafouch/meme-studio --skill agent-email-inbox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-email-inbox, .gemini/skills/agent-email-inbox, .github/skills/agent-email-inbox and .opencode/skills/agent-email-inbox in your project.

What does Agent Email Inbox need to run?

Going by SKILL.md and its folder, Agent Email Inbox needs the command-line tools its instructions call (ngrok, cloudflared, npm, curl, brew and npx) and credentials named RESEND_API_KEY and RESEND_WEBHOOK_SECRET. Our summary lists: Python 3; Node.js; A credential in RESEND_API_KEY; A credential in RESEND_WEBHOOK_SECRET.

Does Agent Email Inbox access the network?

SKILL.md names 5 domains. In commands or code: a1b2c3d4.ngrok-free.app, api.resend.com, owasp.org and ngrok.com; the agent is likely to contact these when it follows the instructions. As links in the text: dns.email. This is read from the text; nothing was executed.

Is Agent Email Inbox safe to install?

Our automated static check of SKILL.md flagged 5 warning(s): mentions a paste, webhook or tunnelling service often used to send data out. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Agent Email Inbox use?

No licence was found for Agent Email Inbox or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Agent Email Inbox use?

About 10k tokens (SKILL.md is roughly 41k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Email Inbox?

Skills that share tags, products or a category with Agent Email Inbox: Email Connector (ericrisco/rsc-harness, 180 stars), Aqua Communication (quailyquaily/aqua, 258 stars), Agentmail (sundial-org/awesome-openclaw-skills, 663 stars) and Stripe Apps (fossasia/eventyay, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Email Inbox?

viclafouch (a GitHub user) maintains it in viclafouch/meme-studio, which has 110 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on March 31, 2026.

Source: viclafouch/meme-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.