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 financial-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/financial-statements)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/financial-statements"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/financial-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/financial-statements"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/financial-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 | $0.00127 | $0.06146 |
| Opus 5.5 | $0.00051 | $0.02458 |
| Sonnet 5.5 | $0.00025 | $0.01229 |
| Haiku 4.5 | $0.00013 | $0.00615 |
Grade A, and why
financial-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 — 456 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial Reporting
Important: This skill guides financial-reporting workflows but does not provide financial advice. All statements, memos, and disclosures should be reviewed by qualified financial professionals before use in reporting or filings.
This is the general guideline for financial reporting — financial statements, reporting packages, footnotes and disclosures, technical accounting memos and position papers, management commentary, and financial-review / board / investment-committee decks. Match the guidance to the deliverable you must produce:
- Statements & reporting packages — the workflow below (income statement, trial-balance workbook, monthly summary, balance sheet, cash flow, GAAP presentation ASC 220/210/230, period-end adjustments) with period-over-period comparison and variance.
- Technical accounting memos / position papers / reference guides (impairment, capitalization, revenue recognition, lease/debt) — write the actual technical analysis, scaffolded: (1) entity/business background — nature of operations, offerings, customers, primary expense categories; (2) the governing ASC cited at subsection level, with every criterion, scope exception, and definitional component of the cited subsections enumerated and individually assessed — a correct gist that omits a listed exception or half of a two-part definition is incomplete; (3) the comparison the standard's chosen path requires — and only that path: a qualitative (step-0) assessment provides a substantive section for each qualitative factor — relevant macroeconomic conditions, industry and market considerations, cost factors, financial performance, entity-specific events — writing the actual conditions that apply (with figures and named developments) and tying each to management's specific facts, then concludes there; related-standard context that frames the analysis (e.g., ASC 730 R&D classification for pre-feasibility costs, feasibility elements under ASC 985) is part of the required substance, not padding, without proceeding to an unrequested quantitative test and without importing public-market indicators for a private reporting unit unless their relevance is explained; when the quantitative path applies, show it (e.g., fair value vs. carrying amount for impairment) with actual and forecast data; (4) for segment/CODM analyses, the CODM's title and review/allocation frequency. These are graded on substance, not brevity — a terse "no adverse change" conclusion fails.
- Slide decks (financial-review, board, investment-committee) — build the reporting content here, then use
financial-presentationsfor deck structure, slide principles, and chart selection.
Clarify like the professional in the room: resolve a genuinely fatal ambiguity (two entities share the requested name; the reporting period is unstated) explicitly before building — but ask only what the requester's role can answer, never re-ask facts the conversation already gave, and list each recurring action once under its correct cadence (an item is monthly or annual, never duplicated as both).
Read Financial Reporting Standards before you build — the build contract these deliverables are graded on, applied as checks on your own work rather than a template: enumerate every named artifact as a grid before building, link derived figures with live formulas, apply only the reporting conventions that fit the requested shape, and work through its verification checklist before returning any workbook.
Whatever the deliverable: before handing over, re-open the delivered file and confirm every explicitly requested file, tab, section, and figure exists under its requested name and is internally consistent.
What ships with it
1 file 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 · 456 lines · 127 tokens per session scan A 21e1e4f0f4d5
financial-statements is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 6,146 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.
financial-statements compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| financial-statementsmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 127 | 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 |