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 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/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/microsoft-copilot-agents-playbook/kitty-explain"><img src="https://agentmods.dev/badge/skills/microsoft/microsoft-copilot-agents-playbook/kitty-explain.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 | $0.00032 | $0.01421 |
| Opus 5.5 | $0.00013 | $0.00568 |
| Sonnet 5.5 | $0.00006 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Explain user-provided content as a single humorous sketchnote-style image in the "Kitty Explain" meme style.
The finished image must combine:
- Photorealistic cat cutouts whose appearance closely matches the supplied cat reference images.
- Hand-drawn sketchnote annotations, diagrams, arrows, labels, and visual metaphors.
- A concise and accurate explanation of the source content.
Reference-image workflow
Complete this workflow before constructing the image-generation request.
- Locate all cat images in the
referencesfolder. - Open and visually inspect every available reference image.
- Confirm that at least one reference image was successfully opened and is readable.
- Select one or more references that best match the roles needed in the sketchnote:
- Use one primary reference for each featured cat.
- Use additional references only when the scene requires multiple cats with visibly different roles.
- Supply the selected reference images to the image-generation request as visual character references.
- For each generated cat, closely preserve the selected reference cat's:
- fur color and pattern
- facial structure and muzzle shape
- eye size, color, and spacing
- ear shape and proportions
- body proportions
- realistic fur texture
- photorealistic cutout appearance
- The cat may have a new pose, expression, prop, or costume appropriate to the explanation, but the cat must remain recognizably consistent with the selected reference.
- If the reference images cannot be accessed, generate the highest-quality photorealistic cute kittens possible that match the intended "Kitty Explain" aesthetic. Maintain:
- realistic fur texture and natural lighting
- realistic kitten anatomy and proportions, including proportionally large bright eyes and large ears
- expressive, meme-like poses and facial expressions
- photographic cutout appearance
- consistent visual style across all cats in the image Do not substitute with cartoonish, doodled, mascot-like, simplified, clip-art, illustrated, low-detail, or obviously AI-generic cat designs. The cats should still feel like authentic "Kitty Explain" characters even when the original references are unavailable.
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.
- 1mo ago Changed · +103 lines · -11 tokens per session f3ff13de58f5
- 2mo 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 (25 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,421 once invoked, about $0.0001 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 2026-08-30.
kitty-explain compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kitty-explainmicrosoft/microsoft-copilot-agents-playbook | Skill | 25 | 1mo ago | MIT | A | 32 | Claude Code, Codex |
| windbg-diagnostic-methodmicrosoft/win-dev-skills | Skill | 499 | 4d ago | MIT | A | 42 | Claude Code |
| windbg-kernel-bugcheck-triagemicrosoft/win-dev-skills | Skill | 499 | 4d ago | MIT | A | 50 | Claude Code |
| windbg-user-heap-corruption-investigationmicrosoft/win-dev-skills | Skill | 499 | 4d ago | MIT | A | 46 | Claude Code |
| windbg-kernel-irp-lifecycle-triagemicrosoft/win-dev-skills | Skill | 499 | 4d ago | MIT | A | 58 | Claude Code |
| windbg-kernel-lock-deadlock-triagemicrosoft/win-dev-skills | Skill | 499 | 4d ago | MIT | A | 56 | Claude Code |
| windbg-kernel-verifier-triagemicrosoft/win-dev-skills | Skill | 499 | 4d ago | MIT | A | 54 | Claude Code |