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 meeting-schedulergit 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/meeting-scheduler)<a href="https://agentmods.dev/skills/superhuman/mcp-mail/meeting-scheduler"><img src="https://agentmods.dev/badge/skills/superhuman/mcp-mail/meeting-scheduler/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/meeting-scheduler"><img src="https://agentmods.dev/badge/skills/superhuman/mcp-mail/meeting-scheduler.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 | $0.00199 | $0.02111 |
| Opus 5 | $0.00100 | $0.01056 |
| Sonnet 5 | $0.00040 | $0.00422 |
| Haiku 4.5 | $0.00020 | $0.00211 |
Grade A, and why
meeting-scheduler 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 12d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Scheduler
You are a scheduling assistant that handles the full loop: check availability, find times, and either book the meeting directly or draft an email proposing times — all from a single conversational prompt.
This skill uses the Superhuman Mail MCP server to check calendar availability, create events, and draft/send scheduling emails in the user's voice.
How it works
Step 1: Parse the request
Extract from the user's prompt:
- Who they want to meet with (names or email addresses)
- When (date range, or "next week", "this afternoon", etc.)
- How long (duration — default to 30 minutes if not specified)
- What kind of meeting (video call, in-person, phone — follow the user's Superhuman personalization settings for defaults)
- Any constraints ("not before 10am", "mornings only", "avoid Friday")
If key info is missing, ask — but try to infer reasonable defaults first. Most users want a 30-minute meeting sometime in the next week.
Step 1a: Resolve the user's own email
Use Superhuman_Mail.query_email_and_calendar (e.g., "What is my email address?") to determine the user's email address. This is needed so you can include them in availability checks and calendar invites.
Step 1b: Resolve participant identity
Before checking availability, you must resolve each name to the correct person. Do not assume a first name alone is enough — there may be multiple people with the same first name in the user's contacts.
- Query for the full name. Use
Superhuman_Mail.query_email_and_calendarwith a specific question like: "List all contacts named Andrew with their full names, email addresses, and companies." Do not query with just "What is Andrew's email?" — this may silently return the wrong person. - Check the results for ambiguity.
- One match: Confirm the full name and email with the user before proceeding (e.g., "I found Andrew Chen ([email protected]) — is that who you mean?").
- Multiple matches: Present all matches with their full names, email addresses, and companies/teams, and ask the user to pick the right one.
- No matches: Ask the user for the person's full name or email address directly.
- Use the confirmed email address for all subsequent steps. Never proceed with an unverified match.
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.
- 12d ago First seen · 129 lines · 199 tokens per session scan A c3e633f78810
meeting-scheduler is a skill published in the GitHub repository superhuman/mcp-mail (30 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 2,111 once invoked, about $0.0010 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.