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 sap-power-platform-integration-architectgit 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/sap-power-platform-integration-architect)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/sap-power-platform-integration-architect"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/sap-power-platform-integration-architect/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/sap-power-platform-integration-architect"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/sap-power-platform-integration-architect.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 | $0.00196 | $0.01962 |
| Opus 5.5 | $0.00078 | $0.00785 |
| Sonnet 5.5 | $0.00039 | $0.00392 |
| Haiku 4.5 | $0.00020 | $0.00196 |
Grade A, and why
sap-power-platform-integration-architect 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 6d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advise on SAP ↔ Microsoft architecture: answer straight away with clearly stated assumptions, then let the user refine the answer by sending back a pre-filled template. Position the options, pick documented patterns, explain the trade-offs, and deliver a short answer in chat plus an HTML report.
Flow: Answer (with assumptions) → Refine (template) → Re-answer. Don't open with a questionnaire.
Instructions
-
Classify the question (it can be several at once):
- Connectivity – how to connect SAP to Power Platform / Copilot Studio →
references/decision-guide.md. - Assistant positioning – Joule vs Microsoft 365 Copilot vs Copilot Studio, and how they work
together →
references/positioning-guide.mdpart A. - Where to extend – in SAP (Fiori, key-user, ABAP Cloud, SAP Build/BTP) or with Power Platform
→
references/positioning-guide.mdpart B. When positioning leads to a Microsoft-side build, continue with connectivity so the answer ends with a concrete pattern.
- Connectivity – how to connect SAP to Power Platform / Copilot Studio →
-
Extract what's known, assume the rest. Read the request and every uploaded file (requirements, landscape description, existing architecture) with the available file or code tools. Fill the fact sheet in
references/decision-guide.md(section 1); for positioning questions also capture where users work, scope (SAP-only or cross-system), SAP release, what Joule already covers, and team skills. For every decisive fact that's missing, choose the most common or most plausible value for the user's context. Tag every fact with its source:user,document: <file name>orassumption. Don't ask questions first; the only exception is a request so ambiguous that no sensible assumption exists (then ask one short question). -
Check that the guidance is current. If a Microsoft Learn tool or web search is available, check the pages marked verify in
references/sources.mdthat matter for this case (at most six lookups) and note anything that changed: new auth options, preview → GA, retirements. Prefer Microsoft Learn and SAP Help over blogs. If no lookup tool is available, use baseline mode and state the baseline date fromreferences/sources.md. -
Decide. For connectivity, apply
references/decision-guide.md(sections 2–4): one primary pattern, at most two alternatives, and the identity chain. For positioning, apply the criteria and rules inreferences/positioning-guide.md: mark each relevant option asrecommended,complementaryornot a fit, and say how they work together. Give each reason in terms of the user's facts. Set confidence tohighonly when no decisive fact is an assumption. If an assumption would flip the recommendation, say which one and what you'd recommend instead. -
Answer in chat, under ~250 words plus the refine section. Connectivity format:
**Recommended:** <pattern name in plain words> (confidence: <high|medium|low>) **Why:** 2–4 bullets tied to the user's facts **Flow:** <consumer> → <connector> → <middleware> → <SAP system> **Identity:** <who SAP sees and how the token travels> **Alternatives:** <pattern name> – <when it would be better> (max 2) **Before you build:** top 5 prerequisites, each with the role that owns it **Assumptions:** the key assumptions, each marked "(assumed)", and which one could change the answer **Report:** <file name> attached · <"checked on Microsoft Learn <date>" | "baseline <date>">Positioning format (Joule vs Copilot Studio, or where to extend):
**Short answer:** one or two sentences **Use <option> for:** … · **Use <option> for:** … **How they work together:** <option name> – one line each **For your case:** recommended / complementary options tied to the user's facts **Assumptions:** the key assumptions, each marked "(assumed)" **Watch-outs:** availability to verify, identity foundation, what not to rebuild **Report:** <file name> attached · <check status>
What ships with it
8 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.
- 6d ago First seen · 132 lines · 196 tokens per session scan A 65aac82c7398
sap-power-platform-integration-architect is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 196 tokens to every session and 1,962 once invoked, about $0.0008 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 2026-11-02.
sap-power-platform-integration-architect compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sap-power-platform-integration-architectmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 196 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | 2d ago | MIT | A | 46 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 555 | 4d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 253 | yesterday | MIT | A | 106 | Claude Code |
| telnyx-messaging-hosted-curlteam-telnyx/ai | Skill | 225 | today | MIT | A | 45 | Claude Code |