verify-email

verify-email is a skill for Claude Code from CeDJeY/mailpit-mcp-server. It costs 72 tokens per session (766 once invoked), scanned A, original, MIT.

A check for emails captured by Mailpit, a test mailbox that collects emails sent by an application. It waits for the expected message, examines its content and links, and reports whether it passes or fails the requested checks.

In plain words
What is it for?
Use it to check welcome emails, invoices, and other application-generated messages, including their text, HTML, links, and compatibility with email clients.
Why use it?
It helps confirm that an application sent the right email and that the message is structured and usable. It also distinguishes a missing email from an email that was routed somewhere other than the test mailbox.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mailpit plugin — 2 skills, 1 MCP server shipped together

Good fit Use it to check welcome emails, invoices, and other application-generated messages, including their text, HTML, links, and compatibility with email clients.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cedjey/mailpit-mcp-server/verify-email
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 CeDJeY/mailpit-mcp-server --skill verify-email
Clone the repo
git clone --depth 1 https://github.com/CeDJeY/mailpit-mcp-server

Made for: Claude Code.

Or install mailpit, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

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 verify-email

README.md
[![agentmods](https://agentmods.dev/badge/skills/cedjey/mailpit-mcp-server/verify-email.svg)](https://agentmods.dev/skills/cedjey/mailpit-mcp-server/verify-email)
Your own site
<a href="https://agentmods.dev/skills/cedjey/mailpit-mcp-server/verify-email"><img src="https://agentmods.dev/badge/skills/cedjey/mailpit-mcp-server/verify-email.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 766 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 $0.00072 $0.00766
Opus 5 $0.00036 $0.00383
Sonnet 5 $0.00014 $0.00153
Haiku 4.5 $0.00007 $0.00077

Measured 7d ago against content hash 9eaf51dec39d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verify-email 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 7d 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.

plugin/skills/verify-email/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify an email in Mailpit

Verify an email captured by the Mailpit test mailbox using the mailpit MCP tools.

Prerequisite: the email must actually be routed here

Mailpit only holds emails the application sent to Mailpit's SMTP port. Verification therefore assumes: (1) the app under test is configured to send to this Mailpit instance, and (2) the action that produces the email has been (or will be) triggered — know what to expect, where it's sent, and roughly when, before you wait for it. If routing hasn't been proven in this project yet — or anything below times out unexpectedly — switch to the route-mail-to-mailpit skill and confirm routing with a canary first; otherwise a FAIL may just mean "the email went somewhere else", which can also be a safety problem (a real SMTP provider receiving test mail).

Input

From the user's request, determine:

  • query — a Mailpit search query narrowing down the email: to:[email protected], subject:"welcome", from:, tag:, or a combination. If the user gave nothing specific, use get_message with id latest instead of waiting.
  • checklist — any structure/content requirements the user stated (must contain a greeting with the user's name, a confirmation link, an unsubscribe footer, etc.).

Steps

  1. If the email is expected to arrive as a result of a just-triggered action, call wait_for_message with the query (default timeout is fine; it also accepts messages that arrived a few seconds before the call). Otherwise search_messages / get_message(latest).
  2. get_message with the found ID — review subject, sender, recipients, text and HTML bodies, attachment list.
  3. get_message_links — enumerate the URLs without requesting them (safe for auth-protected and one-click action links). If the email contains action links (confirm, reset, unsubscribe), do NOT run check_links — it performs real GETs and could trigger them; verify action links by structure instead (correct host, expected path, token present). Otherwise run check_links with follow: true, and treat 302/401/403 on auth-protected links as expected rather than broken.
  4. If there is an HTML body: check_html — note compatibility warnings relevant to mainstream clients (Gmail, Outlook, Apple Mail); ignore exotic ones unless the user cares.
  5. Look for general defects regardless of checklist: unrendered template variables ({{name}}, %FIRST_NAME%), placeholder or missing images, empty sections, mojibake/encoding artifacts, obviously wrong personalization.
  6. If the user provided a checklist, verify every item explicitly.

Read the full file on GitHub · 32 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. 7d ago First seen · 32 lines · 72 tokens per session scan A 9eaf51dec39d

Subscribe to this mod's changes

verify-email is a skill published in the GitHub repository CeDJeY/mailpit-mcp-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 766 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

test-warp-ui

Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.

warpdotdev/warp · 55 tokens

test-electron-app

Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…

PostHog/posthog-foss · 112 tokens

pyats-dynamic-test

Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.

automateyournetwork/netclaw · 61 tokens

trailblaze

Use when working with Trailblaze — natural-language device control for coding agents across iOS, Android, and web, with replayable .trail.yaml files as the artifact. Trigger on mentions of Trailblaze, the trailblaze CLI, .trail.yaml files, trailmaps, waypoints, or requests to drive / author / debug / run UI tests on…

block/trailblaze · 115 tokens

Detox Mobile Testing

Gray-box end-to-end testing for React Native apps with Detox. Covers .detoxrc.js configuration, build and test commands, matchers, device.launchApp control, automatic synchronization, and macOS CI pipelines.

PramodDutta/qaskills · 48 tokens