agentmods.dev

outlook-assistant: Instructions file for Claude Code

CLAUDE.md

outlook-assistant CLAUDE.md is an instructions file for Claude Code from littlebearapps/outlook-assistant. It costs 6,149 tokens per session, scanned B, original, MIT.

Repository instructions for an MCP server that accesses Microsoft Outlook through Microsoft's Graph API, including sign-in and safety controls.

In plain words
What is it for?
Use them when working on Outlook actions, device-code or browser sign-in, mock data, tests, or the local authentication server.
Why use it?
They explain how to install, authenticate, test, and inspect the server without guessing which login method or command to use.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is littlebearapps/outlook-assistant's own configuration. It tells Claude Code how to work on outlook-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything outlook-assistant configures →

not rated 39repo changed 23d ago B scan 6,149 tokens original MIT
View source ↗ littlebearapps/outlook-assistant littlebearapps.com
Reuse

Borrowing it

Nothing to install: this file belongs to littlebearapps/outlook-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/littlebearapps/outlook-assistant/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/littlebearapps/outlook-assistant

Made for: Claude Code.

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-assistant CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/littlebearapps/outlook-assistant/claude-md/github.svg)](https://agentmods.dev/instructions/littlebearapps/outlook-assistant/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/littlebearapps/outlook-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/littlebearapps/outlook-assistant/claude-md/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-assistant CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/littlebearapps/outlook-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/littlebearapps/outlook-assistant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,149 This file is loaded in full into every session.
When invoked 6,149 The same file — it is already loaded in full.
Security scan B 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 $0.06149 $0.06149
Opus 5.5 $0.02460 $0.02460
Sonnet 5.5 $0.01230 $0.01230
Haiku 4.5 $0.00615 $0.00615

Measured 23d ago against content hash 637d9096dbf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

outlook-assistant CLAUDE.md scanned grade B 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 23d 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

**Client ID without env vars** (plugin marketplaces with static `mcp.json`): `auth action=authenticate clientId=<GUID>` validates and saves it to `~/.outlook-assistant-config.json` (0600, atomic) via `auth/client-config.
CLAUDE.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Outlook Assistant

MCP server for Microsoft Outlook via Graph API (v3.14.1). 22 tools across 9 modules. Runtime Node ≥ 18.18; dev tooling (lint-staged hook, npm run inspect) needs Node ≥ 22.22.1.

Commands

npm install              # Install dependencies (run first)
npm start                # Start MCP server
npm run auth-server      # Start OAuth server on :3333 (browser auth only)
npm test                 # Run Jest tests
npm run test-mode        # Start with mock data (USE_TEST_MODE=true)
npm run inspect          # MCP Inspector for interactive testing
npx kill-port 3333       # Kill auth server if port blocked
node index.js --version  # Print version and exit (also -v); --help for usage

Authentication

Device code flow (default — recommended for remote/headless; no auth server, SSH tunnel, or port forwarding needed):

  1. Call auth tool with action=authenticate → returns a code + URL (device-code by default)
  2. Visit the URL on any device, enter the code, and sign in
  3. Call auth tool with action=device-code-complete → tokens saved

Browser redirect flow (alternative, localhost only):

  1. Start the auth server: npm run auth-server (needs OUTLOOK_CLIENT_ID/OUTLOOK_CLIENT_SECRET env vars)
  2. Call auth tool with action=authenticate, method=browser → returns a URL
  3. Open the URL → Microsoft login → grant permissions → tokens saved automatically

Full walkthrough: docs/how-to/getting-started/connect-outlook-to-claude.md. The MCP server reads its own credentials from .mcp.json inline kc_get calls.

Azure prerequisites:

  • Add platform: Authentication > Add a platform > Mobile and desktop applications > check nativeclient URI
  • Enable "Allow public client flows" in Authentication > Advanced settings
  • Use a private/incognito browser for microsoft.com/devicelogin (avoids cached session interference)

Client ID without env vars (plugin marketplaces with static mcp.json): auth action=authenticate clientId=<GUID> validates and saves it to ~/.outlook-assistant-config.json (0600, atomic) via auth/client-config.js, then signs in. Resolution is lazy everywhere (AUTH_CONFIG.clientId is a getter; TokenStorage.getClientId()): OUTLOOK_CLIENT_ID → MS_CLIENT_ID → saved file. A different env value wins, so the tool refuses rather than saving. Device code needs no secret; outlook-auth-server.js (browser) stays env-only.

Read the full file on GitHub · 209 lines

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. 23d ago Changed · +1 lines · +183 tokens per session 637d9096dbf0
  2. 24d ago Changed · +30 lines · +2,312 tokens per session f9aa1e0acb2e
  3. 25d ago Changed · +5 lines · +361 tokens per session scan A → B 1746a33fdb54
  4. 26d ago Changed · +14 lines · +924 tokens per session 2ebc6d29b305
  5. 28d ago Changed 293c485801a1
  6. 1mo ago Changed · +2 lines · +49 tokens per session 4c52c0b88368
  7. 1mo ago First seen · 157 lines · 2,320 tokens per session scan A 083ba4e556ae

Subscribe to this mod's changes

outlook-assistant CLAUDE.md is an instructions file published in the GitHub repository littlebearapps/outlook-assistant (39 stars, last pushed yesterday), licensed MIT. It adds 6,149 tokens to every session, about $0.0246 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIsBuilding agentsClaude Codeaiai-agentscalendarclaudecontacts
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens