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 anasahmed07/Outlook-Classic-MCP --skill outlookgit clone --depth 1 https://github.com/anasahmed07/Outlook-Classic-MCPWrote 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/anasahmed07/outlook-classic-mcp/outlook)<a href="https://agentmods.dev/skills/anasahmed07/outlook-classic-mcp/outlook"><img src="https://agentmods.dev/badge/skills/anasahmed07/outlook-classic-mcp/outlook/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/anasahmed07/outlook-classic-mcp/outlook"><img src="https://agentmods.dev/badge/skills/anasahmed07/outlook-classic-mcp/outlook.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 | $0.00239 | $0.02578 |
| Opus 5 | $0.00120 | $0.01289 |
| Sonnet 5 | $0.00048 | $0.00516 |
| Haiku 4.5 | $0.00024 | $0.00258 |
Grade A, and why
outlook 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outlook
You have tools whose names begin with outlook_ that operate on the user's actual Microsoft Outlook account. They read and write live data — sent mail goes out, deleted items move to Deleted Items, accepted invites notify organizers. Treat write operations the way you would treat any user-visible action: confirm intent first.
When to use this skill
Activate whenever the user wants to do something with their Outlook data. The user does not need to say "Outlook." Triggers include:
- Mail: "any new emails from X?", "draft a reply to that thread about Y", "forward Bob's note to the team", "clean out my inbox", "save the attachment from Sarah's email"
- Calendar / meetings: "what do I have Friday?", "schedule 30 min with Alice next Tuesday", "make that meeting recurring weekly", "decline the 4pm", "what time is the all-hands?"
- Contacts: "what's Carlos's email?", "phone number for the legal team contact"
- Tasks: "remind me to send the report Monday", "mark the budget task done"
- Categories / rules / OOO: "tag that email as Important", "is my OOO still on?", "turn off the rule that auto-files Jira mail"
If outlook_* tools are not available in the session, the underlying integration isn't installed yet. Don't guess or improvise — instead, read references/setup.md and walk the user through installing it (Windows + classic Outlook + a one-line install + restart their MCP client). After install they restart the client and the tools appear.
Tool catalog
All tools are prefixed outlook_. Memorize the categories; consult references/tools.md for exact parameters and return shapes the first time you reach for one.
| Category | Tools |
|---|---|
list_mails, search_mails, get_mail, send_mail, reply_mail, forward_mail, move_mail, delete_mail, mark_mail, save_attachments |
|
| Folders | list_folders, create_folder |
| Calendar | list_events, get_event, create_event, update_event, delete_event, respond_event |
| Contacts | list_contacts, search_contacts (incl. org directory), get_contact, resolve_name |
| Tasks | list_tasks, create_task, complete_task |
| Categories | list_categories, set_category |
| Rules | list_rules, toggle_rule |
| Out-of-Office | get_out_of_office (read-only) |
| Account | whoami |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 128 lines · 0 tokens per session scan A 9ca2bd7879d5
outlook is a skill published in the GitHub repository anasahmed07/Outlook-Classic-MCP (25 stars, last pushed 1mo ago), licensed MIT. It adds 239 tokens to every session and 2,578 once invoked, about $0.0012 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
Daily brief / morning catch-up (Local MCP)
Use when the user asks "what's on my plate today", "catch me up", "morning brief", or wants a summary of their day across calendar, reminders and email. The single most common multi-step automation. Powered by Local MCP.
Inbox to action — triage, reply & schedule (Local MCP)
Use when the user wants to deal with their inbox — find what needs a response, draft replies, and turn emails into calendar events or reminders. Captures the common email→read→reply→schedule workflow. Powered by Local MCP.
Email on Mac (Local MCP)
Use when the user wants to read, search, summarize, draft or triage their Apple Mail / Gmail / Outlook / iCloud email on a Mac. Powered by Local MCP's local Mail tools — no API keys.
Messages & team chat on Mac (Local MCP)
Use when the user wants to read or search iMessage, Microsoft Teams, Slack, WhatsApp or Signal on their Mac — things cloud connectors can't reach. Powered by Local MCP, local-only.
Teams & Slack on Mac (Local MCP)
Use when the user wants to read or search Microsoft Teams or Slack on their Mac — including channels and DMs that the Graph/Slack APIs make hard to reach. Powered by Local MCP, reading the local app stores.
Calendar & scheduling on Mac (Local MCP)
Use when the user wants to check their calendar, find availability, or create/update/delete events on a Mac (Apple Calendar / EventKit). Powered by Local MCP — local, no OAuth.