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 3-statementsgit 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/3-statements)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/3-statements"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/3-statements/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/3-statements"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/3-statements.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 | $0.00116 | $0.02755 |
| Opus 5.5 | $0.00046 | $0.01102 |
| Sonnet 5.5 | $0.00023 | $0.00551 |
| Haiku 4.5 | $0.00012 | $0.00276 |
Grade A, and why
3-statements 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complete an Existing Three-Statement Template
Populate an existing integrated income statement (IS), balance sheet (BS) and cash flow (CF) framework. Deliver a separately named workbook copy with live formulas, evidenced inputs and an honest reconciliation status. The template determines the layout, periods and scope; this skill does not design a new financial model.
When NOT to Use
- No existing framework, blank workbook, or general Excel cleaning, formatting or formula work: use xlsx instead. Ask for the intended template before proceeding if the user says one exists; never silently create a replacement layout.
- Discounted cash flow valuation: use dcf-valuation. Leveraged buyout or sponsor returns: use lbo-model.
- Reviewing or auditing a completed model without filling a framework: outside this skill's scope.
- Explaining actual-vs-plan movements in the completed statements: use variance-commentary. Assembling support for auditor requests: use audit-evidence-package. Ad-hoc analysis of loose spreadsheet or CSV data: use dataset-analysis-report.
- Tax returns, regulatory submissions, transactions and personalized investment recommendations are outside scope.
Quick Start
User: "Complete this IS/BS/CF template using the attached annual reports."
1. Inspect the identified workbook with xlsx; preserve an original.
2. Map reported figures, approved forecast drivers and missing inputs.
3. Complete only in-scope input cells and formulas in a copy.
4. Recalculate, run applicable checks and deliver the output structure below.
Missing workbook: request its attachment or accessible link; do not build a model.
Workflow
1. Locate the workbook and settle material context
Use the supplied workbook path/handle. If the user identifies a remote workbook,
locate it with m365_search-SearchM365 (sources=["files"]) or
sharepoint_onedrive-SearchDrive, then read it with sharepoint_onedrive-ReadFileContent. Search only for that workbook; do not browse unrelated
files. Confirm entity, accounting basis, reporting currency/scale, actual periods,
forecast horizon and deliverable. Ask one focused core-AskUserQuestion when ambiguity blocks
safe progress, bundling related missing facts rather than repeated approvals.
What ships with it
4 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.
- 2d ago First seen · 218 lines · 116 tokens per session scan A bfde6d85928e
3-statements is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 2,755 once invoked, about $0.0005 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.
3-statements compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 3-statementsmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 116 | Claude Code, Codex |
| dcf-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 14 | Claude Code, Codex |
| comps-analysisNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 13 | Claude Code, Codex |
| lbo-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 19 | Claude Code, Codex |
| lbo-modelanthropics/financial-services | Skill | 41k | 11d ago | Apache-2.0 | A | 57 | Claude Code |
| 3-statement-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |
| merger-modelNousResearch/hermes-agent | Skill | 262k | today | MIT | A | 18 | Claude Code, Codex |