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 VKirill/claude-lane-stack --skill project-designgit clone --depth 1 https://github.com/VKirill/claude-lane-stackWrote 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/project-design)<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/project-design"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/project-design/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/project-design"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/project-design.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 | $0.00000 | $0.01171 |
| Opus 5.5 | $0.00000 | $0.00468 |
| Sonnet 5.5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
project-design 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 21d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project design
Load ui-ux-pro-max. One kit: Google DESIGN.md files. No MASTER.md.
Info (print and stop)
If $ARGUMENTS is exactly info:
print the block below verbatim (Russian), then stop. Do not extract. Do not spawn design-lead.
project-design — роутер дизайна lane-stack
Что делает
- Грузит ui-ux-pro-max (поиск стилей, a11y, стек, brand/, banner-design/).
- Пишет полные Google DESIGN.md: корень + каждый UI-app.
- Не пишет design-system/**/MASTER.md и не вызывает --persist.
Кто пишет файлы
- Агент design-lead (терминал: сессия = dev-orchestrator, cwd = проект; Lane Pilot: lane_pilot_specialist role design-lead).
- Онбординг: project-onboarder, если has_ui и DESIGN.md ещё нет.
- Lane writer — только если owns_paths включает DESIGN.md. Иначе match, не invent.
Файлы (все полные, не указатели)
- docs/DESIGN.md — общий бренд, voice, Surfaces (web + social).
- apps/<name>/docs/DESIGN.md — полный файл той поверхности
(cabinet, marketing, …). Те же секции, что у корня. Токены из кода этого app.
Как открыть эту шпаргалку
- /lane-stack:project-design info
- или: lane-stack:project-design info
- или: project-design справка
- каталог всех процессов: /lane-stack:info
Как запустить работу (новая сессия оркестратора)
1) Весь продукт (сайт + кабинет + остальные UI-apps)
Первичный дизайн-анализ. Spawn design-lead, MODE=extract.
Пройди все UI-apps. Полные файлы в docs/DESIGN.md и apps/<name>/docs/DESIGN.md.
Палитру не выдумывай. Ран не открывай.
2) Одна поверхность + корень
Первичный дизайн-анализ. Spawn design-lead, MODE=extract, APP=cabinet.
Обнови docs/DESIGN.md и apps/cabinet/docs/DESIGN.md. Ран не открывай.
3) Новый продукт, UI ещё нет
Spawn design-lead, MODE=seed. Search --design-system, пиши DESIGN.md.
Не --persist, не MASTER.md.
4) Новая страница в живом UI
«планируем, не запускай». Сверь корневой и app DESIGN.md.
Search --design-system только дыры, вмержи в DESIGN.md этой поверхности.
После «делай» — ран. Writer match DESIGN.md того app.
5) Баннер / соцсети
Load ui-ux-pro-max → brand/ + banner-design/.
Размеры и voice → Surfaces в корневом и marketing DESIGN.md.
6) Слоп / ревью вёрстки
Не этот скилл. /lane-stack:web-design info
Агент design-lead MODE=audit. Код — ран.
UI-ран
- Нет нужного DESIGN.md → сначала design-lead, потом запуск писателя (терминал: run-init; Lane Pilot: lane_pilot_specialist role design-lead, потом lane_pilot_dispatch_writer).
- Task read_first: docs/DESIGN.md и apps/<app>/docs/DESIGN.md.
- Не клади DESIGN.md в owns_paths, если исход не токены/доки.
Поиск (локально, без сети)
python3 ~/.agents/skills/ui-ux-pro-max/scripts/search.py "<query>" --domain ux
python3 ~/.agents/skills/ui-ux-pro-max/scripts/search.py "<query>" --design-system -p "Name" -f markdown
python3 ~/.agents/skills/ui-ux-pro-max/scripts/search.py "<query>" --stack nuxtjs
Нельзя
- «см. корень» вместо полного apps/*/docs/DESIGN.md
- Claude Plan mode и ~/.claude/plans/
- выдумывать hex при MODE=extract
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.
- 21d ago Changed 0064de3b1b86
- 1mo ago Changed · +4 lines · -78 tokens per session f8c9035f109e
- 1mo ago First seen · 88 lines · 78 tokens per session scan A 6999ecc62c3b
project-design is a skill published in the GitHub repository VKirill/claude-lane-stack (124 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,171 tokens. 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
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.
creation-flow-prototype
A workflow for creating an interactive prototype before building a medium-sized or larger project with a user interface. It uses the prototype to confirm what the product should look and do like.
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…
amby-design
Design the UI — wireframes, component specs, and design tokens — with a sign-off gate.
republic-design
Republic-style UX design reviewer and scorer for pitch decks, landing pages, and investor-facing materials. Applies Republic.com's design DNA (financial-grade trust, data-forward, restrained elegance) to score and improve any visual artifact. Use when user says "republic", "republic style", "score design", "polish…