microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.
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 skills add microsoft/cat-agent-skills --skill case-packetgit clone --depth 1 https://github.com/microsoft/cat-agent-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/microsoft/cat-agent-skills/case-packet)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/case-packet"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/case-packet/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.
<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/case-packet"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/case-packet.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.00316 |
| Opus 5.5 | $0.00020 | $0.00126 |
| Sonnet 5.5 | $0.00010 | $0.00063 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
case-packet 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 today.
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.
What it actually says
Case Packet
Purpose
Terminal artifact: the complete case packet on first touch - the retail equivalent of the NCR.
When to use
End of every return case.
Inputs
governed.json (full payload).
Steps
- Validate against the contract; escalations and fraud-signal holds lead.
- Packet: case facts with citations, reason code, determination + clause, recommendation, missing-evidence list, fraud signals (factual), customer response draft in the right tone, and the manager exception-request draft when the customer asked for one (#5.1).
- Mark DRAFT - a human authorises any refund, exchange or decline.
Output
CASE-.md - terminal artifact.
Grounding requirements
Every claim cites order, receipt, history, clause or config.
Constraints
- Never authorise a refund, release funds, adjudicate fraud, dispose inventory or book a carrier (plugin boundary).
- Signals appear as signals; the packet never calls the customer a fraud.
Escalation / uncertainty
hold_for_review packets route to asset protection with the signal citations attached.
What ships with it
7 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.
- today First seen · 27 lines · 49 tokens per session scan A 3cf87fbf337a
case-packet is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 316 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
shopify-admin-gift-message-extraction
Read-only: extracts gift messages, gift recipients, and gift flags from order custom attributes and notes for fulfillment teams to print on packing slips.
amazon-listing
Amazon listing CRUD via the category flat-file (Add Products via Upload). Create a variation family (parent + colour/size children), update attributes, change parent-child relationships, and delete SKUs — all in one template round trip. Also covers the end-to-end sourcing flow: a supplier link (e.g. 1688) → extract…
amazon-invoice
Generate tax invoices from Amazon Seller Central order data using browser extraction and PDF generation.
invoice-generation-automation
Generate professional invoices automatically with custom branding, payment terms, line item details, tax breakdowns, and integration with accounting systems.
evo-ocr-preprocess-extract
Preprocesses receipt images and extracts text using Tesseract OCR with optimal settings for receipt layouts.
evo-receipt-parse-export
Parses OCR text from receipts to extract dates and total amounts using keyword-priority matching and regex, writes results to Excel.