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 perniemann/pnCore --skill pn-html-to-videogit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-html-to-video)<a href="https://agentmods.dev/skills/perniemann/pncore/pn-html-to-video"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-html-to-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/perniemann/pncore/pn-html-to-video"><img src="https://agentmods.dev/badge/skills/perniemann/pncore/pn-html-to-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 | $0.00118 | $0.02176 |
| Opus 5 | $0.00059 | $0.01088 |
| Sonnet 5 | $0.00024 | $0.00435 |
| Haiku 4.5 | $0.00012 | $0.00218 |
Grade A, and why
pn-html-to-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 7d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML-to-video (programmatic video)
When to use
- Repeatable marketing cuts, plugin demos, changelog videos, social variants where same input = identical output is a requirement.
- Data-driven explainers: chart races, annotated screen recordings, caption-synced narration.
- You own the visual — it is an HTML/CSS/JS layout you authored, not a model-generated scene.
- Animation runtime is already GSAP, Lottie, CSS, or Three.js and you want to record it frame-accurately.
Use pn-generative-video-pipelines instead when the scene must be invented by a model (characters, environments, stylized footage) and some frame-to-frame variation is acceptable.
Stack comparison
| Tool | Model | Key fit | Requires |
|---|---|---|---|
| Hyperframes (heygen-com/hyperframes) | HTML + data-* attributes, Puppeteer+FFmpeg, Frame Adapters |
Agents, non-interactive CLI, catalog blocks, GSAP/Lottie/Three.js | Node ≥22, FFmpeg |
| Remotion | React components as frames, <Video>, <Audio>, <Sequence> |
React-native teams, programmatic lambda render | Node, ffmpeg |
| Motion Canvas | TypeScript scene graph, imperative animation primitives | Precise mathematical animation, explainer-style graphics | Node, ffmpeg |
Choose Hyperframes when the agent is authoring compositions autonomously (non-interactive CLI, catalog hyperframes add), or when the composition is HTML-first.
Choose Remotion when the codebase is already React and the team prefers component-based composition.
Choose Motion Canvas when the animation is diagram- or explainer-heavy with precise timing control.
HTML composition contract
All three tools share a similar concept: a stage with timed clips. The canonical attributes (illustrated via Hyperframes) are:
<!-- Stage declares composition identity and dimensions -->
<div id="stage"
data-composition-id="my-video"
data-start="0"
data-width="1920"
data-height="1080">
<!-- Video clip on track 0 -->
<video
id="clip-1"
data-start="0"
data-duration="5"
data-track-index="0"
src="intro.mp4"
muted playsinline>
</video>
<!-- Image overlay on track 1, appears at 2s -->
<img
id="overlay"
class="clip"
data-start="2"
data-duration="3"
data-track-index="1"
src="logo.png">
<!-- Audio bed on track 2 at 50% volume -->
<audio
id="bg-music"
data-start="0"
data-duration="9"
data-track-index="2"
data-volume="0.5"
src="music.wav">
</audio>
</div>
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.
- 7d ago First seen · 158 lines · 118 tokens per session scan A 6ff94b2cf13f
pn-html-to-video is a skill published in the GitHub repository perniemann/pnCore (0 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 2,176 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
typescript
TypeScript coding conventions, best practices, and patterns for writing clean, maintainable code.
ax-java-audio
Use when writing Java code with dev.axllm:ax for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.
generate-images-with-firebase-ai
Use when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API vs Vertex AI, hitting quota, billing or App Check failures, getting empty or image-only responses, sending a user photo as input, controlling…
slides
Create and edit presentation decks as single self-contained HTML files with a live, editable preview and print-to-PDF export. Use when the user wants slides, a deck, or a presentation.
invokeai-image-gen
Generate images using InvokeAI's local API. Use when asked to generate, create, or make images with InvokeAI, FLUX.2 Klein, Z-Image Turbo, FLUX, or SDXL models. Supports text-to-image generation, automatic model detection, image download, and parameter selection based on model architecture.
storytelling-with-data
Apply storytelling principles to create, review, and improve data visualisations and data-driven communications. Use when the message or story of a data communication (chart, dashboard, infographic, data-driven deck or report) needs structuring or review, or when structuring narrative arcs, hooks, or aha moments in…