Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/VKirill/claude-lane-stacknpx agentmods add skills/vkirill/claude-lane-stack/page-prototypeWrote 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/vkirill/claude-lane-stack/page-prototype)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/page-prototype"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/page-prototype/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/vkirill/claude-lane-stack/page-prototype"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/page-prototype.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00094 | $0.01777 |
| Opus 5.5 | $0.00038 | $0.00711 |
| Sonnet 5.5 | $0.00019 | $0.00355 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
page-prototype 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.
Page prototype
One HTML file per screen + shared kit. Gray boxes. Real copy if a brief exists. Open in a browser.
Not a designed page. Not a writer lane. Not Vue. Not npm.
Info (print and stop)
If $ARGUMENTS is info: print the block below verbatim, then stop.
page-prototype — серый HTML-вайрфрейм + общий kit.
Диск
<repo>/.agents/prototypes/
_kit/proto.css proto.js один раз, не править под страницу
INDEX.md
site/<slug>/index.html публичная страница
site/<slug>/empty.html
app/<app>/<slug>/index.html экран продукта (= apps/<app>)
flows/<flow>/01-<slug>.html
Куда класть
- лендинг / статья / оффер → site/<slug>/
- кабинет / apps/<имя> → app/<имя>/<slug>/
- воронка → flows/<flow>/NN-<slug>.html
Не плодить copy/ и seo/.
Kit (только эти виджеты)
slider · tabs · accordion · toggle · modal · mobile menu
Разметка: data-proto-* как в references/shell.html
href kit: site/ и flows/ → ../../_kit/ · app/ → ../../../_kit/
Превью 24ч: htmlshare.pro
один файл: publish.py --one
пачка: publish.py --bundle (index.html + style.css + script.js + _kit)
повтор: тот же URL из .host.json · новая страница — новая папка · --new = новый URL
Источник текста
1 .agents/copy/pages/<slug>.md
2 .agents/seo/** brief
3 иначе [LABEL]
Нельзя
- россыпь html в корне · hex бренда · Tailwind · Vue · npm/CDN
- своя анимация вместо proto.css
Disk
.agents/prototypes/
_kit/proto.css
_kit/proto.js
INDEX.md
site/<slug>/index.html
| Ask | Path |
|---|---|
| Публичная страница | site/<slug>/index.html |
| Состояние | site/<slug>/<state>.html |
| Экран продукта | app/<app>/<slug>/index.html |
| Клик-путь | flows/<flow>/01-<slug>.html |
- If
_kit/missing: copyreferences/kit/proto.cssandproto.jsthere. Do not edit the kit per page. - If
INDEX.mdmissing: copyreferences/INDEX.template.md. - Copy
references/shell.htmlinto the page folder. Fix the two../../_kit/paths if this isapp/(../../../_kit/). Fill slots. Delete unused widgets. Do not invent a second CSS/JS stack. - Update INDEX. If a copy brief exists, one-line
prototype:. - If the human asked to open / share / preview, publish to
https://htmlshare.pro(24h, then gone; disk stays). Same page folder → same URL (script writes.host.jsonand sendsid). New slug/folder → new POST, new URL. Expired id → new URL, rewrite.host.json.--newonly if they asked for a fresh link.
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.
- 1mo ago Changed · +8 tokens per session c6a239d4135d
- 1mo ago First seen · 140 lines · 86 tokens per session scan A 7ff06735288f
page-prototype is a skill published in the GitHub repository VKirill/claude-lane-stack (124 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,777 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
brand-tokens
A reference library of visual design rules for well-known brands, including colors, fonts, corner shapes, and explanations of each brand's visual style. Design tokens are reusable values that keep an interface's appearance consistent.
ui-aesthetic
A set of visual design rules for making web pages and components look consistent and readable. It covers icons, colors, typography, spacing, text, accessibility contrast, layout, and restrained animation.
web-stylebook-design
Use BEFORE building, auditing, improving, or redesigning any frontend UI (a page, screen, component, dashboard, form, checkout, chat, or developer console). Confirms audit coverage and change depth, then calls the Web Stylebook MCP to evaluate visual design, user-facing copy and information structure, behavior…
ui-ux-pro-max
UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation. Searchable local…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons.