claude

claude is a skill for Claude Code, Codex from lobster-kit/mcp-server-lobstermail. It costs 0 tokens per session (1,043 once invoked), scanned A, original, MIT.

A set of tools for creating and using temporary email inboxes at the lobstermail.ai domain.

In plain words
What is it for?
Use it to create purpose-specific inboxes, receive incoming messages and codes, wait for email, or send messages from an agent-controlled address.
Why use it?
It gives an agent an inbox for sign-ups, verification messages, confirmations, monitoring, and sending email without using the developer’s personal address.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create purpose-specific inboxes, receive incoming messages and codes, wait for email, or send messages from an agent-controlled address.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lobster-kit/mcp-server-lobstermail/claude
Install

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.

Any agent
npx skills add lobster-kit/mcp-server-lobstermail --skill claude
Clone the repo
git clone --depth 1 https://github.com/lobster-kit/mcp-server-lobstermail

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for claude

README.md
[![agentmods](https://agentmods.dev/badge/skills/lobster-kit/mcp-server-lobstermail/claude/github.svg)](https://agentmods.dev/skills/lobster-kit/mcp-server-lobstermail/claude)
Your own site
<a href="https://agentmods.dev/skills/lobster-kit/mcp-server-lobstermail/claude"><img src="https://agentmods.dev/badge/skills/lobster-kit/mcp-server-lobstermail/claude/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.

agentmods 80×15 button for claude

Your own site · 80×15
<a href="https://agentmods.dev/skills/lobster-kit/mcp-server-lobstermail/claude"><img src="https://agentmods.dev/badge/skills/lobster-kit/mcp-server-lobstermail/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,043 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01043
Opus 5.5 $0.00000 $0.00417
Sonnet 5.5 $0.00000 $0.00209
Haiku 4.5 $0.00000 $0.00104

Measured 2mo ago against content hash 84d290de847e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude 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 2mo 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.

skills/claude/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LobsterMail

You have access to LobsterMail — real @lobstermail.ai email inboxes. Create them instantly, receive email in real-time, send email. No setup, no API keys, no human signup required.


When to Use This

Use LobsterMail whenever the task involves email — proactively, without waiting to be asked:

  • User needs to sign up for a service → create an inbox, use it, read the verification email
  • User needs a temporary or dedicated email address → create one
  • Task requires receiving a confirmation, receipt, or code via email → create an inbox and wait
  • User wants to monitor for incoming email → create an inbox and poll
  • User wants to send an email from an agent-controlled address → use send_email (Tier 1+)

If a service asks for an email during a task, don't ask the user for theirs — create a LobsterMail inbox and use it.


Inbox Naming

Always pick a meaningful name. Prefer identity-based names when you know who/what the inbox is for:

Situation What to do
You know a name/org create_inbox with name + org
Purpose-driven create_inbox with preferred: ["billing-bot", "billing"]
No context create_inbox with no args → gets [email protected]

Examples of good names: [email protected], [email protected], [email protected]

Dots are cosmetic: sarah.shield = sarahshield.


Common Flows

Verification code:

  1. create_inbox with a meaningful name
  2. Use the address to sign up / trigger the email
  3. wait_for_email with from filter and reasonable timeout (60–120s)
  4. get_email to read the full body safely

Monitoring:

  1. create_inbox once, save the inbox ID
  2. Poll with check_inbox periodically, or wait_for_email in a loop

Sending:

  1. create_inbox if you don't have one already
  2. send_email — requires Tier 1+ (Free Verified or above). You can send HTML-only emails (body_html without body_text); a plain text fallback is auto-generated by stripping tags.

Read the full file on GitHub · 104 lines

Changes

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.

  1. 2mo ago First seen · 104 lines · 0 tokens per session scan A 84d290de847e

Subscribe to this mod's changes

claude is a skill published in the GitHub repository lobster-kit/mcp-server-lobstermail (0 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,043 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

safe-email-operations

Use email through the bundled mcp-email-server MCP server, diagnose bounded non-secret state, and hand account or credential setup to a user-operated CLI or authenticated local UI.

Wh1isper/mcp-email-server · 39 tokens

nornweave-api

Give AI agents their own email inboxes using the NornWeave API. Use when building email agents, sending/receiving emails programmatically, managing inboxes, retrieving threads, searching messages, or integrating with email providers (Mailgun, SES, SendGrid, Resend). NornWeave provides LLM-ready markdown parsing and…

DataCovey/nornweave · 77 tokens

pipefy-members-email-webhooks

Use this skill when the user wants to manage pipe membership, send or read card inbox emails, use email templates, or manage webhooks.

pipefy/ai-toolkit · 35 tokens

servicenow-platform-utilities

ServiceNow cross-domain platform helpers — send notification email, render deployed Flow Designer flows to Mermaid and read flow metadata, fetch data-classification and application metadata, list activity subscriptions, and push MetricBase time-series via the servicenow-api MCP server. Use when the agent needs a…

Knuckles-Team/servicenow-api · 156 tokens

mailbuttons

Wire up a governed email inbox for an AI agent using Mailbuttons. Use this skill whenever the user wants to give an agent, app, bot, or workflow its own email address; set up sending or receiving email for an agent; add an agent inbox, sender allowlist, or email webhook; or integrate "Mailbuttons", "mbag", or "email…

mailbuttons/mcp-server · 153 tokens

shipmail

Modern email for your business. Inboxes, calendars, newsletters, bookings and an AI assistant, plus transactional email and an API for your agents. Operate mailboxes, agent inboxes, calendars, booking pages, newsletters, webhooks, and related account resources through the Shipmail MCP server. Use when the user asks to…

shipmail-to/shipmail-mcp · 108 tokens