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 covenant-compliance-checkgit 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/covenant-compliance-check)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/covenant-compliance-check"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/covenant-compliance-check/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/covenant-compliance-check"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/covenant-compliance-check.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 | $0.00144 | $0.03486 |
| Opus 5.5 | $0.00058 | $0.01394 |
| Sonnet 5.5 | $0.00029 | $0.00697 |
| Haiku 4.5 | $0.00014 | $0.00349 |
Grade A, and why
covenant-compliance-check 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Covenant & Borrowing-Base Check
Test borrower figures against the covenants as the credit agreement defines them, and show the work.
Scope
Business-workflow boundary: a standalone facility/borrower monitoring worksheet led by the governing agreement and amendments, not completion of a covenant tab inside an integrated model. The agreement's definitions, applicability, verified inputs, exclusive states, independent flags, and borrowing-base eligibility rules remain mandatory. Model figures may be sourced inputs, not a reason to populate or repair the model.
Do: extract defined terms and thresholds, compute each test as defined, show inputs and arithmetic, cite the governing section, and flag what could not be tested.
Do not: declare an event of default, a breach, a waiver, a cure, or acceleration; characterise headroom as comfortable or tight; or recommend an action. A computed result is not a legal determination — that belongs to the banker and counsel. See the credit-decision gate in references/house-rules.md.
When NOT to Use
- Completing an integrated three-statement model or its embedded covenant schedule — Finance
3-statementsif available. A separately requested agreement-led monitoring review may proceed as a distinct artifact, but do not populate the model. Followreferences/house-rules.md. - Building the underlying financial spread — use
financial-statement-spreadinstead. - Drafting memo narrative — use
credit-memo-narrativeinstead. - Formatting, charting, or restyling an existing workbook — use
xlsxinstead.
Quick Start
For "verify this compliance certificate", identify the governing agreement and amendments first; compute its defined terms from verified inputs; retain every untestable covenant as NOT TESTED.
Tool routing
- Check actual connector availability; use
GetPluginConfigwhen an expected plugin capability is missing. Do not assume a named vendor or optional Finance skill is connected. - For Microsoft 365 record sets use
ExecuteSql; for topic/content discovery useSearchM365. Read located files withReadFileContent(fullfor supported document text;downloadfor exact bytes or spreadsheets). Scope reads to the borrower, purpose, and permissions. - Use available configured connector tools for their documented fields. If none supply an item, follow the existing source order and retain the correct gap marker; never claim a tool ran when it did not.
- Delegate file construction to
xlsx,docx, orpptxas specified below. Inline output is an inline draft, not a saved file. Report a save only from the action tool's successful result.
What ships with it
3 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 · 199 lines · 144 tokens per session scan A 526ae5a4f8a7
covenant-compliance-check is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 3,486 once invoked, about $0.0006 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.
covenant-compliance-check compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| covenant-compliance-checkmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 144 | Claude Code, Codex |
| expense-review-policyopenai/openai-cookbook | Skill | 77k | 2d ago | MIT | A | 17 | Claude Code, Codex |
| audit-supportanthropics/knowledge-work-plugins | Skill | 35k | yesterday | Apache-2.0 | A | 45 | Claude Code |
| kyc-doc-parseanthropics/financial-services | Skill | 41k | 11d ago | Apache-2.0 | A | 49 | Claude Code |
| ma-playbookalirezarezvani/claude-skills | Skill | 29k | 3d ago | MIT | A | 29 | Claude Code |
| fiscalisteromainsimon/paperasse | Skill | 2.6k | 3d ago | MIT | A | 320 | Claude Code, Codex |
| subcontractor-payment-trackerdatadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction | Skill | 397 | 20d ago | MIT | A | 25 | Claude Code, Codex |