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 grab-my-filesgit 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/grab-my-files)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/grab-my-files"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/grab-my-files/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/grab-my-files"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/grab-my-files.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 | $0.00129 | $0.00731 |
| Opus 5 | $0.00064 | $0.00365 |
| Sonnet 5 | $0.00026 | $0.00146 |
| Haiku 4.5 | $0.00013 | $0.00073 |
Grade A, and why
grab-my-files 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 11d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grab My Files
When to use
Invoke when the user says anything like:
- "export all produced files" / "package everything"
- "zip up my files" / "bundle my files"
- "give me everything you made" / "download all the outputs"
If the user names a subset ("just the PDFs", "only the report"), honor that and zip only the matching files, but still follow the rules below.
How to export
- Inspect the folder. List
/app/created/recursively so nested outputs (e.g./app/created/charts/foo.png) are included, not just top-level files. - Decide what goes in. Include every produced file except:
- any previous export archive (files named
all_files_produced_*.zip), and - hidden/system junk (
.DS_Store,Thumbs.db,*.tmp, dotfiles).
- any previous export archive (files named
- Prune old exports after the new one is written. Build the new archive
first, then delete any other
all_files_produced_*.zipin/app/created/. Doing it in this order means a failed build never destroys the user's previous bundle, and no old export gets nested inside the new one. - Handle the empty case. If nothing qualifies, tell the user there are no produced files to export and stop — do not create an empty zip.
- Name the archive
all_files_produced_<YYYYMMDD_HHMMSS>.zip— a sortable, UTC timestamp — and write it to/app/created/. - Preserve structure. Keep the relative folder layout inside the zip so files restore to the same subfolders they came from.
- Deliver it. Return the finished
.zipto the user as a download — don't just report that it was created. In Copilot Studio, writing the file to/app/created/surfaces it as a downloadable attachment; make sure the user gets that link.
Confirm to the user
After the zip is written, reply with:
- the archive name (including its timestamp),
- the total count of files packaged, plus a list of up to 50 packaged paths (sorted). If there are more than 50, list the first 50 and say how many additional files were included, and
- a note that the zip is attached and ready to download.
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.
- 11d ago First seen · 52 lines · 129 tokens per session scan A ffbf2fb063a5
grab-my-files is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 731 once invoked, about $0.0006 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 2026-08-30.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…