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 sharepoint-file-creationgit 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/sharepoint-file-creation)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/sharepoint-file-creation"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/sharepoint-file-creation/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/sharepoint-file-creation"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/sharepoint-file-creation.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 | $0.00106 | $0.01341 |
| Opus 5.5 | $0.00042 | $0.00536 |
| Sonnet 5.5 | $0.00021 | $0.00268 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
sharepoint-file-creation 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick reference — the fixed sequence
- Determine what content/format is being asked for and source it (Section 0).
- Write the complete file under
/app/created/only, with a descriptive unique name. - Re-measure the final file's size with the filesystem API. Proceed only if
0 < size_bytes < 4,000,000; otherwise stop and offer options. - Call Create file with the
/app/created/<name>path bound directly as the content input. Never read bytes into the model to populate it or target another directory. - Report: content source, destination, measured size, and upload result.
Treat steps 2–5 as fixed; only step 1 is meant to flex per use case.
0. Determine and source the content
Apply any configured content-generation rules first, including required templates, knowledge sources, data sources, report structures, schemas, or style guides.
When no more specific rules are configured:
- Identify the requested file format and use the appropriate runtime library. Do not default to plain text unless plain text is requested.
- Ground the content in the user's request, available retrieval/knowledge tools, or prior conversation context.
- If a named source cannot be located, or no source can be identified, ask rather than fabricating content.
Produce a complete, correct file before continuing.
1. Generate the file in /app/created/ only
Write the complete file beneath /app/created/ using a SharePoint-safe, sanitized
basename-only, collision-resistant filename. Retain [A-Za-z0-9_-] in the stem, replace
other runs with _, trim separators, and preserve one valid extension. Reject path
separators, .., and control characters; resolve the candidate path and verify it remains
under /app/created/ before writing or uploading.
Use /app/created/ because it is the confirmed path-reference location for Create file.
Other paths may be uploaded as literal path text instead of file content, causing silent
corruption.
Keep bytes inside the runtime: never print, preview, or return generated content through the model. Track the validated path, filename, and byte count internally for upload, but do not expose the sandbox path in normal user-facing responses.
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.
- 1mo ago First seen · 106 lines · 106 tokens per session scan A 11bcae413a81
sharepoint-file-creation is a skill published in the GitHub repository microsoft/cat-agent-skills (93 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,341 once invoked, about $0.0004 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 2026-09-16.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.