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 copilot-studio-mcp-readinessgit 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/copilot-studio-mcp-readiness)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/copilot-studio-mcp-readiness"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/copilot-studio-mcp-readiness/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/copilot-studio-mcp-readiness"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/copilot-studio-mcp-readiness.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 | $0.00145 | $0.02437 |
| Opus 5.5 | $0.00058 | $0.00975 |
| Sonnet 5.5 | $0.00029 | $0.00487 |
| Haiku 4.5 | $0.00015 | $0.00244 |
Grade A, and why
copilot-studio-mcp-readiness 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 20d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review an MCP server against the constraints Microsoft documents for Copilot Studio, and report what will break and where to fix it. You review and specify; you do not connect anything and you do not change the maker's tenant.
Scope, read this before you check anything
Microsoft documents MCP for two Copilot Studio harnesses, and their constraints are different. Establish which one the user is on before you report anything, because a finding from the wrong harness is worse than no finding.
- Standard harness. MCP runs through Power Platform connectors. This is where the documented tool schema issues and the data policy behavior live. Source: Extend your agent with Model Context Protocol, Connect your agent to an existing MCP server, Troubleshooting MCP integration.
- GitHub Copilot harness. MCP is added from the Tools dialog and is in preview. This is where the footprint limits live. Source: Add an MCP server to your agent as a tool (preview).
The Copilot chat harness is out of scope: Microsoft does not document MCP there. Say so rather than guessing.
If the user has not said which harness, ask that one question first. It is the only question worth blocking on.
Instructions
-
Get the artifact, not the description. Ask for at least one of: the
tools/listresponse, the source file that registers the tools, or the OpenAPI file if they took the custom connector route. Review only what you can read. A README describing the server is not evidence about its schemas. -
Run every check below that applies to the harness in play. For each one record a verdict:
- BLOCKER - the server will not work as it stands. A setup that works but is not the recommended approach is not a BLOCKER. Record it as WATCH.
- FIX - it connects, but something breaks or degrades at runtime.
- WATCH - correct today and dependent on product behavior that moves.
- PASS - checked and fine.
- UNKNOWN - not visible in what you were given. Say what you would need.
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.
- 20d ago Changed · +7 lines 1499d47f581d
- 23d ago First seen · 191 lines · 145 tokens per session scan A 567ed36ff07e
copilot-studio-mcp-readiness is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 145 tokens to every session and 2,437 once invoked, about $0.0006 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 2026-10-05.
Other skills, from other repositories
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…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…