html-video is a local tool that turns HTML, CSS, and data into animated MP4 videos using configurable rendering engines and templates. Coding agents use it to create and export videos on a user's machine, with optional AI-generated soundtracks. The catalogue skills operate the tool and its video-generation workflow.
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 nexu-io/html-video --skill frame-pentagram-statgit clone --depth 1 https://github.com/nexu-io/html-videoWrote 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/nexu-io/html-video/frame-pentagram-stat)<a href="https://agentmods.dev/skills/nexu-io/html-video/frame-pentagram-stat"><img src="https://agentmods.dev/badge/skills/nexu-io/html-video/frame-pentagram-stat/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/nexu-io/html-video/frame-pentagram-stat"><img src="https://agentmods.dev/badge/skills/nexu-io/html-video/frame-pentagram-stat.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 | $0.00028 | $0.01172 |
| Opus 5 | $0.00014 | $0.00586 |
| Sonnet 5 | $0.00006 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
frame-pentagram-stat 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 12d 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.
What it actually says
【模板: 瑞士网格数据帧 (Pentagram Stat)】 【意图】单一关键指标 / benchmark 揭示 / 编辑风数据页。视觉提炼自 huashu-design 的 Pentagram 流派 (MIT, © alchaincyf)。
【画布】1920×1080, 纯白底 #ffffff; 叠瑞士网格 — 水平/垂直细线 (黑, opacity 0.04-0.06), 开场 0.7s 内 scaleX/scaleY 从 0 扫入。
【字体】西文 Archivo (900/700/500) 或 Helvetica Neue; 中文 Noto Sans SC Bold。理性、紧凑、负字距。
【主结构 (时间轴, 默认 4s)】
- 0.0-0.7s 网格线扫入 (scaleX/scaleY 0→1, cubic-bezier(0.16,1,0.3,1))。
- 0.5-1.6s 右侧巨大数字锚点 (font-size ~1020px, weight 900, 黑, opacity 0.07) 从下方 8% 升入并淡现, bleed off 右边缘。
- 0.7s 红色 eyebrow label (uppercase, letter-spacing 6px,
#E63946) fadeUp。 - 0.85s 主数字 headline (~200px, weight 900) fadeUp; 句点/单位用
#E63946红强调。 - 1.15s 副标 (24px,
#999) fadeUp。 - 1.3s 红色 center rule (高 5px) 从宽 0 → 400px 生长。
- 1.35-1.7s 5 根条形图错峰从底部 scaleY 0→1 生长; 中间一根
#E63946红 + opacity 0.85, 其余黑 opacity 0.12。 - 1.5s 黑色数据底栏 (高 80px) 从 translateY(100%) 滑入; 内含 3 组 stat (红色大数字 + 灰白小标签) + 右侧 system 标签。
【配色纪律】仅用 黑 / 白 / #E63946 红 / 中性灰 #999。严禁其他彩色。红色是唯一强调色, 用在 label / 主数字标点 / center rule / 中间条 / 数据底栏数字。
【内容纪律】
- 必须用用户的真实指标/数字, 严禁 lorem ipsum 或编造 benchmark。
- headline 是一个数字 (≤12 字符); anchor 是它的简写 (≤4 字符) 用作背景巨字。
- 动效用
@keyframes,prefers-reduced-motion下全部停在终态 (静态成图)。 - 单文件 HTML。
What ships with it
5 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.
- 12d ago First seen · 63 lines · 28 tokens per session scan A ffcc720dcfa5
frame-pentagram-stat is a skill published in the GitHub repository nexu-io/html-video (4,567 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,172 once invoked, about $0.0001 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
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-data-chart-nyt
A design template for turning CSV data, JSON, or a written finding into a New York Times-style chart frame for video or social media.
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-data-chart-nyt
A skill for turning CSV or JSON data, or a stated finding, into an editorial-style chart or animated video frame inspired by The New York Times.
frame-flowchart-sticky
SVG curve connectors, sticky-note nodes, and cursor interaction with a whiteboard-brainstorm feel.