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/hookdeck/webhook-skills/microsoft-graph-webhooksnpx skills add hookdeck/webhook-skills --skill microsoft-graph-webhooksgit clone --depth 1 https://github.com/hookdeck/webhook-skillsWrote 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.
[](https://agentmods.dev/skills/hookdeck/webhook-skills/microsoft-graph-webhooks)<a href="https://agentmods.dev/skills/hookdeck/webhook-skills/microsoft-graph-webhooks"><img src="https://agentmods.dev/badge/skills/hookdeck/webhook-skills/microsoft-graph-webhooks.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00094 | $0.02370 |
| Opus 5 | $0.00047 | $0.01185 |
| Sonnet 5 | $0.00019 | $0.00474 |
| Haiku 4.5 | $0.00009 | $0.00237 |
Grade A, and why
microsoft-graph-webhooks 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Microsoft Graph Webhooks
Microsoft Graph delivers change notifications (webhooks) when a resource you
subscribe to — Outlook messages, Teams chatMessages, OneDrive/SharePoint
driveItems, users, groups, presence, and more — is created, updated, or
deleted. There is no HMAC signature and it does not follow the Standard
Webhooks spec. Instead, Graph uses a three-part validation model.
When to Use This Skill
- How do I receive Microsoft Graph webhooks / change notifications?
- How do I respond to the
validationTokenendpoint validation handshake? - How do I validate the
clientStateon a Microsoft Graph notification? - How do I create/renew a Microsoft Graph subscription (they expire fast)?
- How do I decrypt rich notifications with
includeResourceData: true? - How do I handle lifecycle notifications (
reauthorizationRequired,subscriptionRemoved,missed)? - Why is my Microsoft Graph subscription creation failing validation?
The Three-Part Validation Model
- Endpoint validation handshake — On subscription create (and when the
notificationUrlchanges), Graph sendsPOST <notificationUrl>?validationToken={token}with an empty body. You must echo the URL-decoded token back astext/plainwith HTTP 200 within 10 seconds, or the subscription is not created. clientState— An opaque shared secret (max 128 chars) you set when creating the subscription. Graph echoes it in theclientStatefield of every notification. Compare it (timing-safe) to your stored value and reject mismatches — this is what authenticates ordinary notifications.validationTokens(rich notifications only) — When you subscribe withincludeResourceData: true, each POST includes avalidationTokensarray of JWTs signed by the Microsoft identity platform, and the resource data is AES-encrypted. See references/verification.md.
Verification (core)
The two checks every handler needs — the handshake and the clientState compare:
What ships with it
21 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.
- examples/express/.env.example 523 B
- examples/express/package.json 501 B
- examples/express/README.md 1.8 KB
- examples/express/src/index.js 4.7 KB runs code
- examples/express/src/subscribe.js 3.1 KB runs code
- examples/express/test/webhook.test.js 5.5 KB runs code
- examples/fastapi/.env.example 519 B
- examples/fastapi/main.py 4.3 KB runs code
- examples/fastapi/README.md 1.7 KB
- examples/fastapi/requirements.txt 203 B
- examples/fastapi/subscribe.py 2.5 KB runs code
- examples/fastapi/test_webhook.py 5.2 KB runs code
- examples/nextjs/.env.example 505 B
- examples/nextjs/app/webhooks/microsoft-graph/route.ts 4.2 KB runs code
- examples/nextjs/package.json 582 B
- examples/nextjs/README.md 1.4 KB
- examples/nextjs/test/webhook.test.ts 4.9 KB runs code
- examples/nextjs/vitest.config.ts 140 B runs code
- references/overview.md 4.9 KB
- references/setup.md 5.1 KB
- references/verification.md 5.6 KB
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.
- yesterday First seen · 203 lines · 94 tokens per session scan A 0c559d452970
microsoft-graph-webhooks is a skill published in the GitHub repository hookdeck/webhook-skills (84 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,370 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…