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 meeting-prepgit 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/meeting-prep)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/meeting-prep"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-prep/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/meeting-prep"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/meeting-prep.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 | $0.00107 | $0.02611 |
| Opus 5.5 | $0.00043 | $0.01044 |
| Sonnet 5.5 | $0.00021 | $0.00522 |
| Haiku 4.5 | $0.00011 | $0.00261 |
Grade A, and why
meeting-prep 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Prep for upcoming customer conversations
Domain: Sales.
Purpose
Prepare the seller a concise sales meeting brief for one upcoming customer interaction: what matters going in, who is expected, what remains owed or unresolved, which questions to ask, and what outcome to seek without presenting a planned conversation as an agreement.
For full preparation, proactively create meeting materials tailored to the upcoming conversation. Follow the Output section for artifact selection and the Research rules for gathering context. Include account or competitive research only when useful for that call and provide clear value to the seller.
Applicability
Start this procedure when the user requests preparation for an upcoming customer or sales interaction, including a general request such as "prepare me for a meeting" whose target is not yet specified. Do not guess a meeting.
Before a substantive brief, establish the intended interaction, its objective or agenda, and at least one relevant meeting-specific fact. If the interaction or objective cannot be established, return only focused preparation questions.
If timing or participants are unknown, produce a bounded topic-focused brief and mark those sections unknown. An objective or agenda can frame proposed questions and desired outcomes; it does not establish customer history.
Potential Data Sources
These are particularly important for this workflow; use your best judgment to use relevant material already supplied or available through applicable tools or sources you can access. These are options, not a mandatory checklist. If needed information is missing, ask the user to provide the input or context needed.
- Calendar for meeting identity, invite context, agenda, timing, and attendees.
- Meeting Transcripts for prior decisions, objections, commitments, and continuity.
- Email for prior meeting notes, recent questions, and customer-facing context.
- Internal Messaging for internal strategy, blockers, owners, and dependencies.
- Knowledge & Files for prior meeting notes, strategy documents, and assets.
- Record Snapshots & Exports for account, opportunity, renewal, and contact context.
- Sales Intelligence for additional context only when it materially improves preparation.
- Public web sources for the customer's account, company, and industry context, if not available through internal sources.
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 · 164 lines · 107 tokens per session scan A 29b5f831646e
meeting-prep is a skill published in the GitHub repository microsoft/cat-agent-skills (101 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 2,611 once invoked, about $0.0004 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.
meeting-prep compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| meeting-prepmicrosoft/cat-agent-skills | Skill | 101 | yesterday | MIT | A | 107 | 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 |