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/cat-agent-skills/explainer-videonpx skills add microsoft/cat-agent-skills --skill explainer-videogit 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/explainer-video)<a href="https://agentmods.dev/skills/microsoft/cat-agent-skills/explainer-video"><img src="https://agentmods.dev/badge/skills/microsoft/cat-agent-skills/explainer-video.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 | $0.00184 | $0.02057 |
| Opus 5 | $0.00092 | $0.01028 |
| Sonnet 5 | $0.00037 | $0.00411 |
| Haiku 4.5 | $0.00018 | $0.00206 |
Grade A, and why
explainer-video 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 3d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explainer Video
Turns a subject under discussion into a narrated, captioned MP4 that explains it. The output is a
finished video in output/, not a deck and not a script.
When NOT to Use
- Slides for live presenting →
pptx. A deck is not a video. - A single image, diagram or infographic →
image-operations/pptx. - Audio only (podcast, briefing) → call
PodcastGeneratedirectly. - A written explainer (SOP, guide, one-pager) →
docx. - Marketing film, live action, real people's likenesses, licensed footage or music — not possible here. Say so plainly and offer the b-roll style this skill can do.
Workflow
1. Frame the subject (one short round)
Establish, from the conversation first and only then by asking: subject, audience
(newcomer / practitioner / exec), target length (default ~2 minutes ≈ 6-8 beats), and the
angle ("when to use each option", "how it works", "what changed"). Use AskUserQuestion
once — never a chain of questions.
Always ask the visual style in that same card: dark (navy slides, colour-coded sections,
photographic b-roll) or light (white slides, brand accents, sparing photography).
Ask whether they have screenshots to include if the subject is a product, tool or UI walkthrough.
2. Gather (only what the video actually needs)
- Research when it matters — external facts, product capabilities, statistics, "what's new":
use
web_search/web_fetch, or thedeep-research-agentwhen claims need citing. Skip research entirely when the subject is already covered by this conversation or the user's own content. Never research a topic the user has already explained. - Internal subjects — pull from
SearchM365,ReadFileContent, meeting transcripts. Ground every internal claim in what those return. - Screenshots —
Glob input/**/*and check any<attached_files>block. Screenshots are used as supplied: framed, optionally box-highlighted, never regenerated or redrawn, so the product UI stays truthful. Note any UI text you rely on in narration so it matches the pixels.
What ships with it
4 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.
- 3d ago First seen · 157 lines · 184 tokens per session scan A c464697d2a1a
explainer-video is a skill published in the GitHub repository microsoft/cat-agent-skills (63 stars, last pushed yesterday), licensed MIT. It adds 184 tokens to every session and 2,057 once invoked, about $0.0009 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
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…