MoeMail is a temporary email service that creates disposable mailboxes for receiving and sending messages without exposing a user's regular address. It is intended for privacy, spam reduction, and short-lived email needs, and can be self-hosted on Cloudflare.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add beilunyang/moemail --skill skillgit clone --depth 1 https://github.com/beilunyang/moemailWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/beilunyang/moemail/skill)<a href="https://agentmods.dev/skills/beilunyang/moemail/skill"><img src="https://agentmods.dev/badge/skills/beilunyang/moemail/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/beilunyang/moemail/skill"><img src="https://agentmods.dev/badge/skills/beilunyang/moemail/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00830 |
| Opus 5.5 | $0.00015 | $0.00332 |
| Sonnet 5.5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
moemail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MoeMail — Temporary Email for AI Agents
Overview
MoeMail provides disposable email addresses with an agent-first CLI (moemail). Create inboxes, wait for messages, read content, and send emails programmatically.
Install
Install the MoeMail CLI globally when it is not already available:
npm i -g @moemail/cli
Then confirm the binary is available:
moemail --help
Setup
Configure once per environment:
moemail config set api-url https://moemail.app
moemail config set api-key YOUR_API_KEY
Or via environment variables: MOEMAIL_API_URL, MOEMAIL_API_KEY.
Core Workflow: Receive an Email
# 1. Create inbox — capture ONCE, parse both fields
RESULT=$(moemail --json create --expiry 1h)
ID=$(echo "$RESULT" | jq -r '.id')
EMAIL=$(echo "$RESULT" | jq -r '.address')
# 2. Use $EMAIL wherever needed (registration, forms, etc.)
# 3. Wait for message (exits when message arrives or times out)
MSG=$(moemail --json wait --email-id "$ID" --timeout 120)
MSG_ID=$(echo "$MSG" | jq -r '.messageId')
# 4. Read full message content
moemail --json read --email-id "$ID" --message-id "$MSG_ID"
Command Reference
| Command | Required Options | Notable Options |
|---|---|---|
config set |
<key> <value> |
keys: api-url, api-key |
create |
— | --name, --domain, --expiry (1h|24h|3d|permanent) |
list |
— | --email-id (lists messages in mailbox), --cursor |
wait |
--email-id |
--timeout (default 120s), --interval (default 5s) |
read |
--email-id, --message-id |
--format (text|html) |
send |
--email-id, --to, --subject, --content |
— |
delete |
--email-id |
— |
--json is a global flag — it works before or after the subcommand:
moemail --json create --expiry 24h # both work
moemail create --expiry 24h --json
JSON Output Shapes
create: { "id": "...", "address": "[email protected]", "expiresAt": "2025-..." }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 89 lines · 37 tokens per session scan A f49ecee4cf3f
moemail is a skill published in the GitHub repository beilunyang/moemail (2,821 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 830 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-mailbox
Create and use disposable, token-scoped email addresses through a configured Agent Mailbox MCP server. Use for testing signups, email verification, magic links, password resets, one-time codes, inbound messages, attachments, and transactional email flows.
prepare-cloudflare-production-deployment
Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment. Use when setting up or auditing Cloudflare MCP resources, wrangler.jsonc bindings, Worker secrets, Turnstile, Email Sending, GitHub Actions secrets/variables, or GitHub CLI deployment wiring for this…
obsidian-sync
Set up and verify free Obsidian sync (Remotely Save plugin → Davflare WebDAV). Use when a user asks to sync an Obsidian vault to their Davflare drive.
hello-site
Reproduce a Davflare static site with existing MCP tools only (publishsite / imageupload). Use when onboarding or demoing “chat → site”.
ui-and-theme
Frontend/design system skill for the svelteflare monorepo. Use this whenever the user wants to build or modify UI — pages, sections, components, layouts, forms, cards, tables, dialogs, dashboards, or landing pages. Also invoke for anything theme-related: light/dark mode, custom colors, design tokens, typography, or…
auth-db-billing
Backend product systems skill for the svelteflare monorepo. Invoke whenever the user wants to work with auth, sessions, protected routes, users, the database, schema changes, migrations, Stripe billing, subscriptions, paid feature gates, or any server-only logic in the Hono API. Trigger on "add a protected route"…