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 company-profile-packgit 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/company-profile-pack)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/company-profile-pack"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/company-profile-pack/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/company-profile-pack"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/company-profile-pack.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 | $0.00166 | $0.02118 |
| Opus 5.5 | $0.00066 | $0.00847 |
| Sonnet 5.5 | $0.00033 | $0.00424 |
| Haiku 4.5 | $0.00017 | $0.00212 |
Grade A, and why
company-profile-pack 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 2d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Profile Pack
Builds a coverage profile on a public company that a banker can drop into a book: reported facts only, every figure cited with its form, period and as-of date, and every gap left visible.
When NOT to Use
- A single quarter's results or what changed on the call — use earnings-note instead.
- Peer selection and trading multiples — use comps-analysis instead.
- Assembling a pitch or credentials deck — use pitch-deck-skeleton instead.
- Prep for a meeting where relationship history matters — use coverage-meeting-prep-debrief instead.
- Private companies — no public filer record exists; offer to work from an uploaded CIM with document-diligence instead.
- Valuation, price views, or forecasts — outside this skill's scope.
- Acquisition accretion or dilution — use merger-model instead.
- An investment recommendation or committee paper — use ic-memo instead.
Related Skills
Hand off rather than overlap:
- The quarter's results against expectations — use earnings-note instead.
- Comparable company multiples and implied range — use comps-analysis instead.
- Turning the profile into deck pages — use pitch-deck-skeleton instead.
- Meeting prep pack built on mail and calendar history — use coverage-meeting-prep-debrief instead.
- Formatting a document you already have — use docx instead.
Workflow
1. Resolve the company
Resolve the issuer by ticker or name before anything else. On EDGAR,
browse-edgar?action=getcompany&ticker=<TICKER>&type=10-K returns the CIK and filing list in one
small page; use company=<NAME> if there is no ticker. If several issuers match, list them with
ticker and CIK and ask once with core-AskUserQuestion. Never guess between similar issuers —
the wrong one produces an entirely wrong profile.
2. Pull filings and financials
Check input/ first — never re-retrieve a filing the user supplied. Then reach SEC EDGAR through
whatever route the session supports: host-web_search to locate the filing, then open it on sec.gov
(the browser is often the only working route; ask the user to enable it if direct fetches fail).
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.
- 2d ago First seen · 172 lines · 166 tokens per session scan A d6d0ca215e5f
company-profile-pack is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 166 tokens to every session and 2,118 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 2026-11-06.
company-profile-pack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| company-profile-packmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 166 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | today | MIT | A | 39 | Claude Code, Codex |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | today | MIT | A | 28 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 4d ago | MIT | A | 110 | Claude Code |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | today | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 271 | today | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 4d ago | GPL-2.0 | A | 292 | Codex |