microsoft/microsoft-copilot-agents-playbook is a practical learning series about building, grounding, extending, and evaluating agents for Microsoft 365 Copilot. It is intended for people developing declarative agents and covers skills, organizational context through WorkIQ, MCP apps, and evaluation workflows, with the catalogue entry providing a related skill.
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 agentmods add skills/microsoft/microsoft-copilot-agents-playbook/kitty-explainnpx skills add microsoft/microsoft-copilot-agents-playbook --skill kitty-explaingit clone --depth 1 https://github.com/microsoft/microsoft-copilot-agents-playbookWrote 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/microsoft-copilot-agents-playbook/kitty-explain)<a href="https://agentmods.dev/skills/microsoft/microsoft-copilot-agents-playbook/kitty-explain"><img src="https://agentmods.dev/badge/skills/microsoft/microsoft-copilot-agents-playbook/kitty-explain.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00523 |
| Opus 5 | $0.00022 | $0.00262 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
kitty-explain 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 4d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Explain about a given content as a sketchnote-like humorous image of the "Kitty explain" meme style featuring photorealistic kittens/cats.
Cat rendering rules
- Before generating the final image, inspect the file in references/ and prepare to generate kitten images that closely resemble the reference kittens. Pick most suitable cat image from the reference images to generate each cat.
- Each generated cat image should be in a photorealistic cutout style. And it must visibly preserve the selected reference cats' fur pattern, face shape, eye shape, pose, and lighting. The generated cats should not be cartoonish, doodled, mascot-like, simplified, or visually disconnected from the reference images.
- Use props with cats where appropriate: make a cat wear eyeglasses for intellectual ideas, lab coats for experiments, briefcase for businesses, coins for things related to finance, or use other appropriate items.
- Keep playful meme-like expressions.
Overall visual styles
- Use white background.
- Use the instructions above to make cats look photorealistic.
- Use a hand-drawn sketchnote style with scribbled arrows, rough bullet points, messy block diagrams, loose pen lines, speech balloons, and playful labels, but never to the cats themselves.
- Use a Comic Sans-like lettering style for all text.
- Draw visual metaphors like charts for data, the scale of justice for legal, etc. that match the source content.
- Always include a title, and it should end with "explained by cats" or a close variant.
- Include the source URL if the user attached. Truncate long URL then end with "...", especially if the URL comes with query strings.
- Keep the tone playful, comedic and meme-inspired energy, while preserving the meaning of the source.
- Keep visuals simple, not too dense. Don't overdo.
Steps
- Identify the summarized source content into the most important ideas, keeping the explanation accurate and concise, but simple.
- Create a single sketchnote-style image in the style that described above.
- If the source content is missing or unclear, ask the user before generating the final image.
What ships with it
6 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.
- 4d ago First seen · 37 lines · 43 tokens per session scan A 5e8c17492ebc
kitty-explain is a skill published in the GitHub repository microsoft/microsoft-copilot-agents-playbook (23 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 523 once invoked, about $0.0002 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
design
Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro)…
banner-design
Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist…
design-system
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-tech-sharing
OpenDesign internals: how the agent stream, sandbox, and artifacts work — an engineering deep-dive talk. Built as a decision-grade AI literacy deck for engineers, dev community.
slides
Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.