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 Overbrilliant/ob-1 --skill designgit clone --depth 1 https://github.com/Overbrilliant/ob-1Wrote 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/overbrilliant/ob-1/design)<a href="https://agentmods.dev/skills/overbrilliant/ob-1/design"><img src="https://agentmods.dev/badge/skills/overbrilliant/ob-1/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/overbrilliant/ob-1/design"><img src="https://agentmods.dev/badge/skills/overbrilliant/ob-1/design.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 | $0.00082 | $0.28752 |
| Opus 5.5 | $0.00033 | $0.11501 |
| Sonnet 5 | $0.00016 | $0.05750 |
| Haiku 4.5 | $0.00008 | $0.02875 |
Grade A, and why
design-skill 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 today.
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 — 1,869 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Skill
The complete UI/frontend design playbook for ob1 — load this whenever you design or build any user interface.
It is one continuous flow: orchestration → foundations → components & states → behavior & quality → patterns → review. Always begin with Frontend Design (the two-pass method: plan a grounded token system, critique it, then code), then pull in the sections you need. Cross-references like "the color-system section" point to headings below; this file is fully self-contained.
Sections
- Frontend Design —
frontend-design - Anti-Slop —
anti-slop - Visual Hierarchy —
visual-hierarchy - Design Tokens —
design-tokens - Color System —
color-system - Typography —
typography - Spacing & Layout —
spacing-and-layout - Depth & Imagery —
depth-and-imagery - Component States —
component-states - Loading, Empty & Error States —
loading-empty-error-states - Forms & Inputs —
forms-and-inputs - Data Tables —
data-tables - Motion & Animation —
motion-and-animation - Accessibility —
accessibility - Responsive Design —
responsive-design - Tailwind v4 + shadcn/ui —
tailwind-and-shadcn - Landing Page Design —
landing-page-design - Dashboard Design —
dashboard-design - Screenshot Critique Loop —
screenshot-critique-loop - Design Review —
design-review
Frontend Design
Entry point for any "build/design a UI" request. Never start coding immediately. Run two passes: plan (no code) → critique (kill clichés) → build. Ground every choice in the subject's real-world domain — a tax app is not a candy app. Spend boldness in ONE place; keep the surroundings quiet. When in doubt, remove one accessory.
Pass 1 — Plan (no markup yet)
Invent a compact token system and show it to the user BEFORE writing any HTML/JSX. Five parts:
- Color — 4-6 named hex tokens, derived from the subject. e.g. for a fishing-trip planner:
--deep:#0B3C5D --tide:#328CC1 --sand:#F4E4C1 --hull:#1C1C1C --coral:#E84A27. One accent only. Defer ratios/scales to the color-system section. - Type triad — name 3 real fonts with roles + sizes:
display (e.g.
Fraunces 700, 48px/52px), body (Inter 400, 16px/26px), utility (IBM Plex Mono 500, 13px). Defer scale to the typography section. - Spacing — one 8pt scale:
4 8 12 16 24 32 48 64 96. Pick the page gutter (e.g.24) and the section rhythm (e.g.64). Defer to the spacing-and-layout section. - Wireframe — ASCII the layout so structure is argued before pixels:
┌──────────────────────────────┐ │ logo nav [CTA] │ 56px bar ├──────────────────────────────┤ │ H1 display │ │ sub · body │ hero, 64 pad │ [signature element] │ ├───────────────┬──────────────┤ │ card │ card │ 3-up @ ≥1024 └───────────────┴──────────────┘ - Signature element — ONE memorable thing tied to the domain (a tide-line divider, a boarding-pass ticket stub, a ledger rule). Everything else stays calm. Describe it in one sentence.
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.
- today First seen · 1,869 lines · 82 tokens per session scan A 125e21eea5f8
design-skill is a skill published in the GitHub repository Overbrilliant/ob-1 (16 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 28,752 once invoked, about $0.0003 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 2026-09-23.
Other skills, from other repositories
frontend-design
Production-grade UI/UX guidance — not generic AI slop. Triggers on design, UI, frontend, component, styling, layout, make it look good.
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
frontend-philosophy
Visual & UI philosophy (The 5 Pillars of Intentional UI). Understand deeply to avoid "AI slop" and create distinctive, memorable interfaces.
uicraft
Create, improve, audit, and polish distinctive production-grade web interfaces, including marketing/landing pages and personal portfolio sites. Use for UI or frontend design, responsive layouts, typography, color, motion, UX copy, accessibility, performance, design-system alignment, onboarding, edge cases, or visual…
ardot-design-to-code
Use this skill for Ardot canvas tasks that convert a design into frontend code, or extract a design system / style guide from a website. Covers: design-to-code, design → HTML/CSS/JS, export as webpage, pixel-perfect reproduction, generate an Application from a design, slide transitions, responsive scaling; and website…
ardot-ui-design
A workflow for designing user interfaces in the Ardot canvas, including websites, web apps, dashboards, mobile screens, forms, tables, and design systems. A user interface is the screens and controls people use to operate software.