msgraph-files

msgraph-files is a skill for Claude Code, Codex from automateyournetwork/netclaw. It costs 58 tokens per session (1,033 once invoked), scanned A, original, Apache-2.0.

A read-only Microsoft 365 file tool for browsing OneDrive and SharePoint files, their details, versions, and sharing permissions.

In plain words
What is it for?
Use it to list folder contents, find documents, review file history, and check who can access a file.
Why use it?
It lets an agent locate and inspect stored documents without changing files or their access settings.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/automateyournetwork/netclaw/msgraph-files
Any agent
npx skills add automateyournetwork/netclaw --skill msgraph-files
Clone the repo
git clone --depth 1 https://github.com/automateyournetwork/netclaw

Made for: Claude Code, Codex.

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 msgraph-files

README.md
[![agentmods](https://agentmods.dev/badge/skills/automateyournetwork/netclaw/msgraph-files.svg)](https://agentmods.dev/skills/automateyournetwork/netclaw/msgraph-files)
Your own site
<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/msgraph-files"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/msgraph-files.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,033 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00058 $0.01033
Opus 5 $0.00029 $0.00517
Sonnet 5 $0.00012 $0.00207
Haiku 4.5 $0.00006 $0.00103

Measured yesterday against content hash d47295e5fae3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

msgraph-files 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 yesterday.

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.

workspace/skills/msgraph-files/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft 365 Files (read-only)

MCP Server

  • Package: @softeria/ms-365-mcp-server (MIT)
  • Invocation:
    npx -y @softeria/ms-365-mcp-server --read-only --enabled-tools 'drive-item|folder-files'
    
  • Requires: an Entra ID (Azure AD) app registration and delegated Graph scopes. The server handles the device-code sign-in itself via its login tool.

Version 2.0.0 replaced a package that did not exist. Until spec 093 this skill invoked npx -y @anthropic-ai/microsoft-graph-mcp, which 404s on npm, and documented seven graph_* tool names that exist in no server. Every call it described failed. The tool names below were read from the live server's tools/list, not recalled.

Why the --enabled-tools filter is mandatory

The unfiltered server exposes 188 tools measured at ~225,355 tokens — 45× NetClaw's 5,000 token manifest ceiling. It is unusable without a filter. The filter above lands 12 tools at ~4,599 tokens, which fits with little room to spare, so keep it narrow.

Verified tools

Read from the running server, --read-only with the filter above:

Tool What it does
list-folder-files contents of a drive folder
get-drive-item metadata for one item by id or path
list-drive-item-versions version history of an item
list-drive-item-permissions who an item is shared with
list-drive-item-thumbnails available thumbnail renditions
login / verify-login / logout device-code sign-in and session state
list-accounts / select-account / remove-account multi-account handling

There are no graph_* tools. If you find yourself reaching for one, it came from this skill's old text and does not exist.

Workflow: locate and inspect a document

  1. verify-login — is there a live session? If not, login and surface the device code to the operator; never fabricate a sign-in.
  2. list-folder-files from the drive root, then descend
  3. get-drive-item for the candidate — size, timestamps, path
  4. list-drive-item-permissions if the question is about sharing or exposure
  5. list-drive-item-versions if the question is "what changed and when"

Read the full file on GitHub · 86 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. yesterday First seen · 86 lines · 58 tokens per session scan A d47295e5fae3

Subscribe to this mod's changes

msgraph-files is a skill published in the GitHub repository automateyournetwork/netclaw (650 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 1,033 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories

rfp-response-content-generation

Section-by-section proposal drafting agent. Takes the approved Strategy Brief (ToC + Content Strategy Brief), the RFP Tracker list, and the firm's source documents, and produces a complete proposal draft Word document. Drafts each section individually using one of three modes — Adapt, Synthesize, or Placeholder …

pnp/sharepoint-skills · 96 tokens

flashcards-dashboard

Creates an interactive HTML learning dashboard from a source file by extracting key concepts into validated flashcards with source links, hover-detail answers, filters, review tracking, shuffle, and progress tracking. Use when the user says: "Create flashcards from this file" "make an HTML learning dashboard" "turn…

pnp/sharepoint-skills · 115 tokens

kb-ai-review-lite

Minimal KB quality-check skill for SharePoint libraries. It creates missing review columns, writes short review outputs in Markdown, sets review status, records completion time, and schedules the next review by category.

pnp/sharepoint-skills · 44 tokens

library-cleanup

Organizes files in a document library so people and AI can find them easily. Scans all files, summarizes issues (duplicates, empty folders, bad names), recommends a clean structure with a visual before/after comparison, reads file content to propose meaningful rename suggestions, then executes with a TODO checklist…

pnp/sharepoint-skills · 81 tokens

rfp-response-content-finder

Searches the firm's SharePoint document libraries — Capability Library, Content Asset Library, Past Proposals Library, and Standard Positions — to find existing content that matches each requirement or question in the RFP Tracker list. Classifies each row as administrative or substantive before searching, with smart…

pnp/sharepoint-skills · 100 tokens

metadata-completeness-auditor

Audits the metadata quality of a SharePoint document library or list. Scans every item against its required columns, flags missing, blank, or placeholder values, computes a completeness score per item and per column, and saves a self-contained HTML gap-report dashboard to the site. It is strictly read-only — it never…

pnp/sharepoint-skills · 154 tokens