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 onsager-ai/dev-skills --skill ui-designgit clone --depth 1 https://github.com/onsager-ai/dev-skillsWrote 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/onsager-ai/dev-skills/ui-design)<a href="https://agentmods.dev/skills/onsager-ai/dev-skills/ui-design"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/ui-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/onsager-ai/dev-skills/ui-design"><img src="https://agentmods.dev/badge/skills/onsager-ai/dev-skills/ui-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 | $0.00049 | $0.00836 |
| Opus 5.5 | $0.00020 | $0.00334 |
| Sonnet 5.5 | $0.00010 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
ui-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 8d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI design workflow
Scope
This procedure coordinates design tools; repository contracts own the visual system, implementation stack and acceptance checks. Tool installation does not authorize production UI changes, a new aesthetic, credential migration or paid generation. Use the user's established scope without repeated setup per repo.
Prerequisites
Resolve the checkout/ref, read AGENTS.md and the repository's design instructions. Inspect existing components, token sources, generated assets and visual tests. Use harness-operations when capability mapping is needed. The optional user-level tooling is described in integration setup; loading this workflow itself requires no personal installation.
Procedure
- Read the repository-local design brief before selecting a tool. Extract exact source values and semantic roles, including theme variants and source SHA. A generated DESIGN.md or .pen library is a derived design artifact, never a replacement token authority. Keep shared foundations and product layouts separate; do not introduce a reverse dependency between repositories.
- Inspect the live tool catalog and authentication independently for each harness. Stitch is a remote service; pen.dev desktop MCP requires a same-host app/socket. In cloud environments use the supported headless CLI when no app is available. Do not invent a remote pen.dev MCP endpoint or report a configured server as operational. CLI agent-provider authentication is separate from pen.dev authentication and from the calling harness's authentication.
- For Stitch, load the relevant Google Labs skills from the single user-level canonical installation: extract-design-md, design-md, enhance-prompt, manage-design-system, generate-design, extract-static-html, upload-to-stitch or code-to-design. Follow repository policy and available equivalent tools. Framework-specific example output does not authorize a stack migration. Do not install the same vendor skills as both plugins and loose skills.
- Credentials stay in inherited secure variables or the private user credential store. Never extract a key from an MCP config, print it, include it in a prompt, pass it on a command line or commit it. Some upstream upload examples pass an API key as an argument: use authenticated MCP/SDK uploads with in-memory auth instead. Account access does not authorize uploading private source/data; prepare the concrete assets under the user's task scope. Synthetic fixtures are preferable to real transcripts and authenticated personal pages.
- For pen.dev desktop MCP, load read_skill and verify get_app_state against the
intended document before editing. For headless work use the user launcher
~/.local/bin/ui-design pen interactive --out <explicit-artifact-path>. Read the current schema/execute instructions, work in an isolated .pen file, save deliberately and inspect an exported screenshot. Use independent output paths for concurrent harnesses; never let both edit one active document. - Refine a small approved screen or component first. Compare the result with source tokens, the approved design and the existing implementation. Implement in authored frontend sources using existing components/controllers. Preserve server forms, accessibility, security, focus, touch and lifecycle ownership. Regenerate bundles with their owning build tool, never vendor-export them over production files. Run the repository's applicable design, behavioral and pixel checks; review differences before an intentional baseline update.
What ships with it
9 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.
- references/integrations.md 8.3 KB
- scripts/package-lock.json 53 KB
- scripts/package.json 243 B
- scripts/proxy.mjs 265 B runs code
- scripts/run.mjs 3.8 KB runs code
- scripts/run.test.mjs 1.5 KB runs code
- scripts/setup.py 8.0 KB runs code
- scripts/setup.test.py 4.1 KB runs code
- scripts/smoke.mjs 3.0 KB runs code
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.
- 8d ago First seen · 71 lines · 49 tokens per session scan A 6fd036f14bd7
ui-design is a skill published in the GitHub repository onsager-ai/dev-skills (6 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 836 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 2026-10-09.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…