outlook-graph

outlook-graph is a skill for Claude Code from dbhq-uk/outlook-graph-skill. It costs 48 tokens per session (7,612 once invoked), scanned A, original, MIT.

A connector for Microsoft 365 Outlook email and calendars. It lets an agent work with messages and events through Microsoft's Graph service.

In plain words
What is it for?
Use it to read inbox messages, draft or send emails, reply to everyone on a thread, view the calendar, and schedule events.
Why use it?
It provides a defined way to check mail, prepare replies, view availability, and manage calendar events while keeping all original email recipients visible.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is # Download ALL attachments to ./inbox/.

Part of the outlook-graph plugin — 2 skills shipped together

Good fit Use it to read inbox messages, draft or send emails, reply to everyone on a thread, view the calendar, and schedule events.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/dbhq-uk/outlook-graph-skill
agentmods
npx agentmods add skills/dbhq-uk/outlook-graph-skill/outlook-graph

Made for: Claude Code.

Or install outlook-graph, the plugin that ships this one along with the rest of its 2 skills.

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 outlook-graph

README.md
[![agentmods](https://agentmods.dev/badge/skills/dbhq-uk/outlook-graph-skill/outlook-graph/github.svg)](https://agentmods.dev/skills/dbhq-uk/outlook-graph-skill/outlook-graph)
Your own site
<a href="https://agentmods.dev/skills/dbhq-uk/outlook-graph-skill/outlook-graph"><img src="https://agentmods.dev/badge/skills/dbhq-uk/outlook-graph-skill/outlook-graph/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.

agentmods 80×15 button for outlook-graph

Your own site · 80×15
<a href="https://agentmods.dev/skills/dbhq-uk/outlook-graph-skill/outlook-graph"><img src="https://agentmods.dev/badge/skills/dbhq-uk/outlook-graph-skill/outlook-graph.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00048 $0.07612
Opus 5 $0.00024 $0.03806
Sonnet 5 $0.00010 $0.01522
Haiku 4.5 $0.00005 $0.00761

Measured 9d ago against content hash 904d930d763b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

outlook-graph scanned grade A with 1 finding 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 9d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/outlook-graph-calendar.sh, scripts/outlook-graph-mail.sh, scripts/outlook-graph-setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Always read the original message's full `To:` and `Cc:` lists BEFORE creating a reply.** Use a direct API call if `read` truncates: `curl … "/me/messages/<id>?$select=toRecipients,ccRecipients"`. Knowing who's on th
skills/outlook-graph/SKILL.md · 598 lines

How it starts

The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outlook Email & Calendar

Access Microsoft 365 Outlook email and calendar via Microsoft Graph API.

CRITICAL: Replies preserve ALL original recipients (reply-all by default)

reply, mdreply, and followup use Microsoft Graph's createReplyAll endpoint. The new draft includes every To: and Cc: recipient from the original message — not just the sender.

Mandatory rules:

  1. Always read the original message's full To: and Cc: lists BEFORE creating a reply. Use a direct API call if read truncates: curl … "/me/messages/<id>?$select=toRecipients,ccRecipients". Knowing who's on the thread is part of "reading the full body end-to-end" — do not skip it.
  2. After creating any reply draft, confirm the displayed To:, Cc:, and Bcc: lines match what you intended. All three reply commands now print every recipient (not just To[0]). If the list looks short, the original might have had CCs you missed — re-check before sending.
  3. If you genuinely want sender-only, create the reply, then run update to <sender-email> and update cc "" (or manually edit) to trim recipients. Default is "everyone stays in the loop".
  4. Never assume a single-recipient To: means a single-recipient thread. Estate agents, solicitors, accountants, and courts routinely Cc colleagues, assistants, and audit addresses. Dropping those CCs on reply is a real harm — they stop seeing the conversation.

This rule exists because a previous reply silently dropped two CCs (assistant addresses on an estate-agent thread); the recipients had to be looped back in via a follow-up email. Reply-all is now the default to make recipient loss impossible by accident.

CRITICAL: Reading email content

preview is a snippet (first ~200 chars of body), not the full message. NEVER use preview to analyse, summarise, respond to, or report on email content. A short preview does NOT mean a short message — the message can continue for many paragraphs and contain attachments, requests, deadlines, or substantive content not visible in the preview.

Read the full file on GitHub · 598 lines

Files

What ships with it

6 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.

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. 9d ago First seen · 598 lines · 48 tokens per session scan A 904d930d763b

Subscribe to this mod's changes

outlook-graph is a skill published in the GitHub repository dbhq-uk/outlook-graph-skill (2 stars, last pushed 28d ago), licensed MIT. It adds 48 tokens to every session and 7,612 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

domain

When you want to brainstorm and check available .com domains for a new project — brand naming, aftermarket pricing (HugeDomains / Afternic / Sedo / Dan), USPTO trademark screening, and social handle availability. Built on Laura Roeder's "work backwards from availability, not from a name you fell in love with"…

coreyhaines31/makerskills · 232 tokens

company-brain

Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so Claude can answer questions on your team's behalf. Team-scope sibling to second-brain (which is personal-scope). Seven modes — capture (drop something into the right structured dir), compile (process into wiki…

coreyhaines31/makerskills · 322 tokens

slide-deck

When you want to draft, update, convert, or export a slide deck for a React/Next.js slide system (${SLIDEDECKREPO:-$HOME/code/your-slide-deck-site}/src/app/slides/). Writes TypeScript Slide[] arrays using your primitives (Eyebrow, Heading, Accent, Body, BulletList, Divider, TwoCol, GradientText), 12 cycling brand…

coreyhaines31/makerskills · 259 tokens

service-desk

Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…

cbrock84/headcount · 73 tokens

session-cleanup

Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST /api/settings/cleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation.…

hoangsonww/Claude-Code-Agent-Monitor · 67 tokens

toolify

When you want to integrate an external tool, API, MCP server, or service into a project — the wizard walks you through auth, config, env vars, client wrapper code, example usage, and (optionally) a smoke-test. Scoped to Next.js and Rails projects (the two primary stacks). Interactive Q&A pattern — starts with the tool…

coreyhaines31/makerskills · 261 tokens