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 muhammaddadu/outlook-cli --skill outlookgit clone --depth 1 https://github.com/muhammaddadu/outlook-cliWrote 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/muhammaddadu/outlook-cli/outlook)<a href="https://agentmods.dev/skills/muhammaddadu/outlook-cli/outlook"><img src="https://agentmods.dev/badge/skills/muhammaddadu/outlook-cli/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/muhammaddadu/outlook-cli/outlook"><img src="https://agentmods.dev/badge/skills/muhammaddadu/outlook-cli/outlook.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 | $0.00266 | $0.05819 |
| Opus 5 | $0.00133 | $0.02910 |
| Sonnet 5 | $0.00053 | $0.01164 |
| Haiku 4.5 | $0.00027 | $0.00582 |
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 8d 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 — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using the outlook CLI
A locally-installed CLI that wraps the Outlook REST API by piggybacking on the user's existing Outlook Web (OWA) session. There is no API key, no account to configure — if it's installed, it Just Works.
If outlook --version fails, stop and tell the user the CLI isn't
installed. Do not attempt to install it autonomously.
Start every session with outlook context
Run outlook context before your first mail-related action in a
session. It's free (no network, no Chromium) and returns:
{
"user": { "email": "…", "name": "…", "tenant_id": "…" },
"tokenMinutesUntilExpiry": 1408,
"learnings": [
"2026-05-18 | Signs off as Sam",
"2026-05-18 | Prefers terse one-line replies",
"2026-05-18 | 'the team' usually means [email protected]"
],
"learningsFile": "/Users/…/.local/share/outlook-spike/learnings.md"
}
Use user.email to know whose mailbox you're acting on. Use learnings
to adapt your tone, recipient resolution, and default behaviour to what
the user has shown they prefer.
Adapt over time with outlook learn
When you observe something durable, non-obvious, and useful about the user's mail habits, append it:
outlook learn add "Signs off as 'Sam'"
outlook learn add "Drafts to vendors should be HTML with the legal footer"
outlook learn add "When user says 'my boss' they mean [email protected]"
Good learnings have all three properties:
- Durable — true today and likely true next week. Not "the user is in a hurry right now."
- Non-obvious — a fact you couldn't trivially re-derive next time. Skip "user has an inbox."
- Useful — informs how you'd act next time. "User likes pizza" is cute but doesn't change your behaviour.
Don't pollute. A good rule: < 30 entries total. If learnings get noisy,
suggest the user run outlook learn forget <substring> to prune.
Never record sensitive content without asking (financial details, HR context, anything the user might not want a future agent to see). If in doubt, ask: "Want me to remember this for next time?"
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.
- 8d ago First seen · 541 lines · 266 tokens per session scan A e496ecd5c3c7
outlook is a skill published in the GitHub repository muhammaddadu/outlook-cli (2 stars, last pushed 1mo ago), licensed MIT. It adds 266 tokens to every session and 5,819 once invoked, about $0.0013 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.
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.
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.