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 superhuman/mcp-mail --skill welcome-to-superhuman-mailgit clone --depth 1 https://github.com/superhuman/mcp-mailWrote 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/superhuman/mcp-mail/welcome-to-superhuman-mail)<a href="https://agentmods.dev/skills/superhuman/mcp-mail/welcome-to-superhuman-mail"><img src="https://agentmods.dev/badge/skills/superhuman/mcp-mail/welcome-to-superhuman-mail/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/superhuman/mcp-mail/welcome-to-superhuman-mail"><img src="https://agentmods.dev/badge/skills/superhuman/mcp-mail/welcome-to-superhuman-mail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00084 | $0.01273 |
| Opus 5 | $0.00042 | $0.00636 |
| Sonnet 5 | $0.00017 | $0.00255 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
welcome-to-superhuman-mail 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 11d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Welcome to Superhuman Mail
Guide the user through a short, interactive onboarding for Superhuman Mail. Keep it warm, concise, and choice-driven. Do not run account, email, calendar, or send actions until the user chooses them. After the user completes any onboarding task, show the full menu again and ask what they want to try next.
Opening
Welcome the user to Superhuman Mail and explain that they can use it to:
- Search and answer questions across email and calendar.
- Draft, edit, schedule, and send emails.
- Create or update calendar events.
- Use Superhuman features outside this MCP client in Gmail, Outlook, desktop, and mobile apps.
Then present the onboarding as a menu and ask what they want to try first. If the client supports buttons or quick replies, use them. Re-present this same menu after each completed task unless the user says they are done.
Suggested menu:
- Add another email account
- Draft a first email
- Ask questions of my inbox
- Tune tool approval settings
- Use Superhuman in Gmail & Outlook, and apps
- Create or update a calendar event
- Watch video tutorials for more ideas
Add another email account
Tell the user they can add multiple Gmail or Outlook accounts to Superhuman Mail.
If the client supports buttons, show:
- Add account - call the
add_accounttool - Skip for now - continue onboarding
If the user chooses to add an account, call the add_account tool rather than sending a settings link. If the user skips or finishes adding an account, show the onboarding menu again.
Draft a first email
Invite the user to try:
draft an email to [email protected] saying hi.
Explain that Superhuman Mail can create a draft, and the user can edit it in the client or send it as-is after reviewing. Never send without explicit approval.
When the user asks to draft, use the Superhuman Mail drafting tool available in the client. Prefer creating a draft over sending directly. After the draft is created or the user skips, show the onboarding menu again.
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.
- 11d ago First seen · 118 lines · 84 tokens per session scan A 385f54e16a9e
welcome-to-superhuman-mail is a skill published in the GitHub repository superhuman/mcp-mail (30 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,273 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…