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 customer-engagement-and-deal-risk-insightsgit 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/customer-engagement-and-deal-risk-insights)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/customer-engagement-and-deal-risk-insights"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/customer-engagement-and-deal-risk-insights/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/customer-engagement-and-deal-risk-insights"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/customer-engagement-and-deal-risk-insights.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 | $0.00121 | $0.02467 |
| Opus 5.5 | $0.00048 | $0.00987 |
| Sonnet 5.5 | $0.00024 | $0.00493 |
| Haiku 4.5 | $0.00012 | $0.00247 |
Grade A, and why
customer-engagement-and-deal-risk-insights 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Engagement and Deal Risk Insights
Objective
Help a seller identify active deals that need attention, understand when and why momentum changed, and choose a meaningful next action. Combine authorized Microsoft 365 work signals with CRM context when available. If CRM is unavailable, provide customer engagement insights without claiming authoritative pipeline risk.
When to use this skill
Use this skill when a seller asks which deals need attention, whether a deal has lost momentum, what changed with a customer, what is blocking progress, who owns the blocker, or what they can do next. Support both portfolio questions and questions about one deal.
Example requests: “Which active deals should I focus on this quarter?” “What changed with Contoso?” “Where did momentum change?” “Which risks can I actually act on?” “Which quiet deals are still on track?”
Inputs and access
- Use only information the seller is authorized to access. Relevant work signals may include Outlook email, Teams chats and channel messages, calendar activity, meetings and transcripts, documents, and shared files.
- When available, use live CRM accounts, opportunities, stages, forecast categories, value, close dates, owners, next steps, stakeholders, activities, notes, milestones, products, and competitors.
- A seller-uploaded CRM view is a point-in-time snapshot. Retain its date, distinguish its fields from later observations, and never describe it as live.
- Associate a work signal with a specific opportunity only when the mapping is supported. Do not merge activities from different opportunities at the same account.
Workflow
1 Find and prioritize relevant deals
Start with the seller’s active deals when CRM is available. Rank by quarter timing (use the organization’s fiscal quarter when available; otherwise clarify which quarter the seller means if it affects the answer), time left to act, value or exposure, meaningful momentum change, missed commitments, blockers, stakeholder changes, and available seller action. Do not rank on value alone. If CRM is missing, identify customers and engagements from authorized work signals where possible; do not imply the set is a complete pipeline.
What ships with it
2 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 · 150 lines · 121 tokens per session scan A 0598590f9db7
customer-engagement-and-deal-risk-insights is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,467 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.
customer-engagement-and-deal-risk-insights compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| customer-engagement-and-deal-risk-insightsmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 121 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |