microsoft-365

microsoft-365 is a skill for Claude Code from HybridAIOne/hybridclaw. It costs 33 tokens per session (1,347 once invoked), scanned A, original, MIT.

A read-only connector for Microsoft 365, Microsoft's suite of email, calendar, file storage, and collaboration services, through Microsoft Graph.

In plain words
What is it for?
It helps read Outlook mail and calendar events, search OneDrive or SharePoint files, inspect Teams memberships and channels, read messages and chats, and view the user's profile.
Why use it?
It gives an agent access to information without allowing it to send messages, change files, update calendars, or post in Teams.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit It helps read Outlook mail and calendar events, search OneDrive or SharePoint files, inspect Teams memberships and channels, read messages and chats, and view the user's profile.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hybridaione/hybridclaw/microsoft-365
Install

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.

Any agent
npx skills add HybridAIOne/hybridclaw --skill microsoft-365
Clone the repo
git clone --depth 1 https://github.com/HybridAIOne/hybridclaw

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 microsoft-365

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridaione/hybridclaw/microsoft-365/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/microsoft-365)
Your own site
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/microsoft-365"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/microsoft-365/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 microsoft-365

Your own site · 80×15
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/microsoft-365"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/microsoft-365.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 66
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 91
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high System Prompt Leakage · line 156
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
How audits are shown
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 $0.00033 $0.01347
Opus 5 $0.00016 $0.00674
Sonnet 5 $0.00007 $0.00269
Haiku 4.5 $0.00003 $0.00135

Measured 11d ago against content hash 827b0df05d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

microsoft-365 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (m365.cjs), 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.

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.

skills/microsoft-365/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft 365

Use this skill for read-only Microsoft 365 workflows backed by Microsoft Graph.

Scope

  • read the signed-in user's Microsoft 365 profile
  • list or search Outlook messages
  • read calendar events in a requested time window
  • list or search recent OneDrive files
  • list joined Teams, team channels, channel messages, and recent chats
  • interpret common Microsoft Graph auth, permission, and throttling errors

This skill is read-only. Do not send mail, create or update calendar events, modify files, post Teams messages, or change tenant state with this skill.

Credential Rules

HybridClaw stores Microsoft Entra OAuth refresh-token material in encrypted runtime secrets. At request time the gateway mints a short-lived Microsoft Graph access token and injects it only for graph.microsoft.com.

Recommended setup:

hybridclaw auth login microsoft365 \
  --client-id "<entra-app-client-id>" \
  --tenant-id organizations \
  --account [email protected]
hybridclaw auth status microsoft365

Use OAuth login for normal setup. If an operator must manually replace stored Microsoft credential material, advise this order: browser admin at /admin/secrets, /secret set ... in browser /chat or TUI, then hybridclaw secret set ... in a local console.

Use a Microsoft Entra app registration with a localhost/mobile-desktop redirect URI matching the callback URL printed by the login command. The default scope set is read-only: User.Read, Mail.Read, Calendars.Read, Files.Read.All, Sites.Read.All, Team.ReadBasic.All, Channel.ReadBasic.All, ChannelMessage.Read.All, Chat.Read, plus offline_access.

Tenant admins may need to grant consent for the broader Graph read scopes. Never paste client secrets, refresh tokens, or access tokens into chat.

For direct Graph calls outside this helper, configure a route:

hybridclaw secret route add https://graph.microsoft.com/v1.0/ microsoft-oauth Authorization Bearer

Default Workflow

  1. Start by building a helper request:
    node skills/microsoft-365/m365.cjs --format json http-request ...
    
  2. For live reads, prefer the helper run command so the CJS script owns endpoint selection, gateway submission, and auth-error handling.
  3. If using the built-in http_request tool directly, pass only the emitted httpRequest object. Do not handcraft Microsoft Graph requests from memory.
  4. If a call returns 401, 403, Authorization_RequestDenied, or insufficient_claims, stop after the first failure and tell the operator to run hybridclaw auth status microsoft365, verify tenant admin consent, and reconnect with hybridclaw auth login microsoft365 if needed.
  5. If Graph returns 429, respect Retry-After; do not loop retries.

Read the full file on GitHub · 163 lines

Files

What ships with it

1 file 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. 11d ago First seen · 163 lines · 33 tokens per session scan A 827b0df05d6b

Subscribe to this mod's changes

microsoft-365 is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,347 once invoked, about $0.0002 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.