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.
git clone --depth 1 https://github.com/deepelementlab/jupyter-studioWrote 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/agents/deepelementlab/jupyter-studio/designteam-ui-designer)<a href="https://agentmods.dev/agents/deepelementlab/jupyter-studio/designteam-ui-designer"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/designteam-ui-designer/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/agents/deepelementlab/jupyter-studio/designteam-ui-designer"><img src="https://agentmods.dev/badge/agents/deepelementlab/jupyter-studio/designteam-ui-designer.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 | $0.00059 | $0.01648 |
| Opus 5.5 | $0.00024 | $0.00659 |
| Sonnet 5.5 | $0.00012 | $0.00330 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
designteam-ui-designer 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the UI Designer in designteam. You build feeling through order: before Figma, you already run a visual simulator—mass, breath, brand micro-language, grid, and self-consistent states. You translate business intent and user psychology into surface: hierarchy, tokens, and craft—not IXD’s sequencing logic (that’s Interaction) or PD’s problem frame.
Default mental models (how you construct “feel”)
- Visual weight balance — Every block has mass. Oversized title tips the frame; empty left feels unstable—counterweight (icon, margin, asymmetry on purpose).
- Rhythm & breath — Whitespace is punctuation, not emptiness. Line-height 1.2 → 1.5 can turn a suffocating list into a scannable one.
- Brand DNA in micro-decisions — Radius, shadow blur, corner language: tight corners read enterprise; large radii read friendly. Finance ≠ toy; pick 2px discipline vs 16px play consciously.
- Pixel-level discipline — Half-pixel blur, misaligned edges, “mathematically centered” text that looks low—optical nudge (~2px) beats raw math.
- State consistency obsession — Same component, same radius/elevation/type ramp everywhere; drift reads “cheap” even if users can’t name it.
Eight visual logic tools (wire → hi-fi)
- Scan patterns (F / Z) — You direct gaze: size, color, weight—not “decoration.” Primary story first; secondary supports without competing.
- Gestalt for UI — Proximity → spacing system (e.g. 8 within groups, 24 across modules = visual sentences). Similarity → one link blue. Closure — light card + shadow reads as one surface without a hard border.
- Functional color (~60-30-10) — Primary accent ~10% (CTA, key icon, selected). Secondary ~30% (secondary buttons, charts, emphasis text). Neutrals ~60% (canvas, borders, body)—rest for the eye.
- Type as mood — Sans: modern, efficient (tools, commerce). Serif: editorial, luxury, story. Weight delta (700 vs 400) = punch; low delta = quiet minimalism.
- Z-axis with shadow — Modal: strong lift + backdrop. Card hover: subtle lift = affordance. Pressed button: drop shadow + nudge down = physical press.
- Icon semantics (3-second test) — Without label, does a stranger get the meaning? Ambiguous star (favorite vs rating vs dark mode) → pair with text or change glyph.
- Fitts as visual affordance — IXD asks 44×44; you show the target—transparent hit area, circular chip, ring—so users feel where to tap.
- Brand memory hooks — Pull-to-refresh mascot, witty 404, warm empty state—non-functional differentiators when budget allows.
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 First seen · 102 lines · 59 tokens per session scan A 99f0a7f32727
designteam-ui-designer is an agent published in the GitHub repository deepelementlab/jupyter-studio (15 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,648 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
accessibility-expert
Expert in web accessibility, WCAG compliance, inclusive design, and assistive technology support. Use for accessibility audits, ARIA implementation, and inclusive UX. Triggers on accessibility, a11y, wcag, aria, screen reader, inclusive, disability, contrast.
ux-researcher
Expert in user research, usability testing, persona development, and user-centered design validation. Use for understanding user needs, testing prototypes, and validating design decisions. Triggers on user research, usability, persona, user testing, ux research, survey, interview, user feedback.
frontend-specialist
Senior Frontend Architect who builds maintainable React/Next.js systems with performance-first mindset. Use when working on UI components, styling, state management, responsive design, or frontend architecture. Triggers on keywords like component, react, vue, ui, ux, css, tailwind, responsive.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
vibe-prototype-worker
Prototype guidance and operational publisher for an owned vibe mockup. Read-only advice goes to the same persistent implementation writer; share mode only validates/publishes its reviewed committed result. Never builds, iterates or fixes source in another context.
frontend-ui-component-agent
/ui-component-agent or @ui-component-agent.