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-agent-testgit 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-agent-test)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/copilot-studio-agent-test"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/copilot-studio-agent-test/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-agent-test"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/copilot-studio-agent-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00166 | $0.04064 |
| Opus 5.5 | $0.00066 | $0.01626 |
| Sonnet 5.5 | $0.00033 | $0.00813 |
| Haiku 4.5 | $0.00017 | $0.00406 |
Grade A, and why
copilot-studio-agent-test 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 1mo 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Studio agent testing
Runs questions against a Copilot Studio agent through the Microsoft 365 Agents SDK
(CopilotStudio.Copilots.Invoke), captures answers and citations, and writes results to
CSV and JSON for review.
Each question runs in a fresh conversation — the programmatic equivalent of clicking New chat — so no answer benefits from context set by a previous one.
Requires Node.js 22 or later. There is no bundled executable — the tool is a single JavaScript file, so nothing unsigned is executed and endpoint policy has nothing to block.
Invoke it from this skill's directory. Prefer the
nodeform — it is identical on Windows, macOS and Linux, and works in every shell:node scripts/cs-agent-test.cjs <command>Convenience launchers exist if you would rather not type
node:.\scripts\cs-agent-test.cmdon Windows,sh scripts/cs-agent-test.shelsewhere.Examples below use the
nodeform, so they can be copied as-is on any platform.Check Node first. If
node --versionfails or reports below v22, stop and tell the user to install Node.js 22+ from https://nodejs.org — every command will fail until they do.
What this tool does and does not do
Does: send questions, capture answers, extract citations, detect escalation, flag empty turns, check optional required substrings, convert Word Q&A documents into test sets, and assemble a pass/fail report from verdicts it is given.
Does not decide by itself whether an answer is semantically correct. That grading pass is step 3 of the workflow below and is performed by you, by reading each answer against the expected one. The report then carries real pass/fail verdicts. Never fabricate a pass rate the tool did not receive from a grading pass.
First run
Setup collects four values: application (client) ID, tenant ID, environment ID, and agent
schema name. They are written to ~/.cs-agent-test/config.json — the user's home folder,
never this skill folder, so the skill stays shareable. There are no secrets involved: auth is
delegated device-code, so nothing sensitive is ever collected or stored.
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.
- 1mo ago First seen · 343 lines · 166 tokens per session scan A f692bc908a02
copilot-studio-agent-test is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 166 tokens to every session and 4,064 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.