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 business-osgit 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/business-os)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/business-os"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/business-os/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/business-os"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/business-os.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00119 | $0.01456 |
| Opus 5 | $0.00060 | $0.00728 |
| Sonnet 5 | $0.00024 | $0.00291 |
| Haiku 4.5 | $0.00012 | $0.00146 |
Grade A, and why
business-os 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 11d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business OS
Business OS is an operating layer for business work. It works out what outcome is actually needed, picks a proportionate method, does what it can, and is honest about what it cannot verify. It also recognises when repeated work is a candidate for a reusable Skill.
When to use this Skill
Use it for: business decisions, problems, projects, incidents, process design or improvement, ambiguous "sort this out" requests, business communications and meeting outputs, and requests to turn a completed process into a Skill.
Do not use it for: casual chat, a one-line factual lookup, a small rewrite or formatting request, or anything a more specific installed Skill already handles well. For those, just do the task.
Operating loop
Work through these steps mentally for anything beyond a trivial request. Skip stages that add no value for the task at hand.
- Outcome - What result would count as success here? Is the stated request a proxy for a bigger need? Say the outcome back in one line before doing the work.
- Classify the work - Pick a primary type: question, task, decision, problem, project, incident, process, idea/opportunity, document, research, communication, review, strategy, or unknown (investigate until it's classifiable). Work is often hybrid; name a primary type and any secondary ones.
- Size the response - Judge reversibility, financial/legal/security exposure, number of stakeholders, and urgency. Choose:
- Fast - simple, low-risk, obvious. Just do it.
- Structured - needs a short plan, some evidence gathering, or a template.
- Deep - high-impact, ambiguous, regulated, or multi-stage. Load the relevant reference(s) below. Do not apply Deep-path rigour to Fast-path work, and do not give a shallow answer to a Deep-path problem.
- Check what's known versus missing. Separate fact, retrieved evidence, user-supplied information, reasonable inference, and assumption. Only raise a question if answering it changes what you'd do next; otherwise proceed on a stated, labelled assumption.
- Do the work, pulling in one or two relevant references from below, not all of them.
- Verify - did the actual outcome from step 1 get met, not just "was an action taken"? State completion status plainly (complete, complete with caveats, partially complete, blocked, or needs a human decision).
- Capture learning, if it's worth capturing. Only propose a playbook, template, or Skill candidate when the work is genuinely repeatable and valuable, not after a one-off task.
What ships with it
31 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.
- assets/templates/checklist.md 143 B
- assets/templates/company-dna-profile.md 1002 B
- assets/templates/decision-brief.md 596 B
- assets/templates/decision-log.md 165 B
- assets/templates/executive-summary.md 265 B
- assets/templates/lessons-learned.md 476 B
- assets/templates/meeting-brief-and-notes.md 592 B
- assets/templates/project-plan.md 651 B
- assets/templates/recommendation-memo.md 493 B
- assets/templates/risk-register.md 456 B
- assets/templates/skill-candidate-assessment.md 1.1 KB
- assets/templates/skill-improvement-proposal.md 303 B
- assets/templates/skill-specification.md 1.3 KB
- assets/templates/sop-and-process.md 711 B
- assets/templates/stakeholder-map.md 295 B
- metadata.json 861 B
- README.md 3.6 KB
- references/communication-engine.md 1.6 KB
- references/company-dna.md 2.1 KB
- references/decision-engine.md 1.5 KB
- references/executive-lenses.md 2.0 KB
- references/governance-evidence-qa.md 2.7 KB
- references/incident-engine.md 1.4 KB
- references/memory-and-learning.md 1.7 KB
- references/problem-solving.md 1.5 KB
- references/process-engine.md 1.5 KB
- references/project-engine.md 1.1 KB
- references/skill-generator.md 5.3 KB
- references/test-scenarios.md 5.1 KB
- references/work-classification.md 4.3 KB
- references/worked-examples.md 3.6 KB
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.
- 11d ago First seen · 78 lines · 119 tokens per session scan A 9aac26e17f58
business-os is a skill published in the GitHub repository microsoft/cat-agent-skills (66 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,456 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
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…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.