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 agentmods add skills/codemie-ai/codemie-code/msgraphnpx skills add codemie-ai/codemie-code --skill msgraphgit clone --depth 1 https://github.com/codemie-ai/codemie-codeWhat 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 | $0.00204 | $0.04172 |
| Opus 5 | $0.00102 | $0.02086 |
| Sonnet 5 | $0.00041 | $0.00834 |
| Haiku 4.5 | $0.00020 | $0.00417 |
Grade A, and why
msgraph 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 2d 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Graph API Skill
This skill lets you interact with Microsoft 365 services on behalf of the user using the
Microsoft Graph API. The Node.js CLI at scripts/msgraph.js handles everything — no Python
or extra packages needed, only the Node.js that CodeMie already requires.
Setup & Authentication
Check login status first — always run this before any other command:
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js status
Output interpretation:
Logged in as: [email protected]→ proceed with any command belowNOT_LOGGED_IN→ follow the Login Flow belowTOKEN_EXPIRED→ session expired, also follow the Login Flow below
Login Flow (first time or after expiry)
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js login
This opens the system browser for Microsoft authentication (PKCE flow). If the browser
does not open automatically, a URL will be printed in the terminal — navigate to it manually.
After successful sign-in, the token is cached at ~/.ms_graph_token_cache.json and all
subsequent commands run silently.
Use --force to re-authenticate even when already logged in:
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js login --force
When NOT logged in or token expired
If status returns NOT_LOGGED_IN or TOKEN_EXPIRED, tell the user:
"You need to log in to Microsoft first. Run this command in your terminal:
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js loginYour browser will open for Microsoft sign-in. If it doesn't open automatically, a URL will appear in the terminal — navigate to it to complete authentication."
Available Commands
Profile & Org
# Your profile
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js me
# Your manager
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js org --manager
# Your direct reports
node ${CLAUDE_PLUGIN_ROOT}/skills/msgraph/scripts/msgraph.js org --reports
What ships with it
2 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.
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.
- 2d ago First seen · 409 lines · 204 tokens per session scan A 9611b2549d17
msgraph is a skill published in the GitHub repository codemie-ai/codemie-code (276 stars, last pushed 2d ago), licensed Apache-2.0. It adds 204 tokens to every session and 4,172 once invoked, about $0.0010 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…