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 kellykampen/agent-skills --skill remotion-explainer-videogit clone --depth 1 https://github.com/kellykampen/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/kellykampen/agent-skills/remotion-explainer-video)<a href="https://agentmods.dev/skills/kellykampen/agent-skills/remotion-explainer-video"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/remotion-explainer-video/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/kellykampen/agent-skills/remotion-explainer-video"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/remotion-explainer-video.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 | $0.00226 | $0.02360 |
| Opus 5 | $0.00113 | $0.01180 |
| Sonnet 5 | $0.00045 | $0.00472 |
| Haiku 4.5 | $0.00023 | $0.00236 |
Grade A, and why
remotion-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 10d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remotion Explainer Video
Produces a ~15-30s explainer video (MP4 + GIF, with a real royalty-free soundtrack) for whatever the user wants explained — a skill, a feature, a product, a workflow. The video is a sequence of scenes built from a shared, tested visual system, not hand-rolled from scratch each time.
Workflow
1. Understand the subject and set scope
Before writing anything, get from the user (or infer from context and confirm):
- What is this video explaining? Read the actual source (a
SKILL.md, a README, the feature's code) — don't write scene content from a vague gist of what it does. A video that gets the mechanics wrong is worse than no video. - Target length. Default to "quick hype cut" (~20s) unless told otherwise. Longer needs explicit ask — most subjects don't need more than 6 scenes to land.
- Music: does the user have a track already, or should you find one? See
references/pixabay-sourcing.mdeither way — even a user-provided file gets wired in the same way (fade in/out,<Audio>+staticFile()). - Where does this live? Check for an existing Remotion project first (see
references/scaffolding.md) — most of the time this is "add one more video to the project that already has others," not "start from zero."
2. Design the scene sequence
A typical explainer is 5-6 scenes, each a few seconds:
- Boot/title — a typed command (if the subject is a CLI/skill) or a short hook line, then the title.
- The problem — why does this need to exist? Scattered chip/tag visuals reading like overheard complaints work well here.
- The core mechanism — the one diagram that actually explains how it works. This is the scene worth the most design effort; see "Choosing a diagram shape" below.
- A two-word contrast or a short checklist — whatever the subject's second-most-important idea is (two responsibilities, two axes, a set of guardrails/rules).
- A short checklist/gates scene — rules, tiers, or steps, if the subject has them.
- Outro — tagline, install/usage command typed out, link.
What ships with it
10 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.
- assets/templates/Diagram.tsx 7.3 KB
- assets/templates/Scene.tsx 2.4 KB
- assets/templates/theme.ts 1.6 KB runs code
- assets/templates/Typewriter.tsx 1.5 KB
- evals/trigger-eval-draft.json 2.4 KB
- references/ephemeral-lifecycle-pattern.md 3.1 KB
- references/pixabay-sourcing.md 3.7 KB
- references/scaffolding.md 3.6 KB
- scripts/make-gif.sh 834 B runs code
- scripts/render-version.sh 1.1 KB runs code
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.
- 10d ago First seen · 154 lines · 226 tokens per session scan A 194f8246f704
remotion-explainer-video is a skill published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 226 tokens to every session and 2,360 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
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-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.