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 chaxus/ran --skill designgit clone --depth 1 https://github.com/chaxus/ranWrote 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/chaxus/ran/design)<a href="https://agentmods.dev/skills/chaxus/ran/design"><img src="https://agentmods.dev/badge/skills/chaxus/ran/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/chaxus/ran/design"><img src="https://agentmods.dev/badge/skills/chaxus/ran/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 | $0.00035 | $0.00307 |
| Opus 5.5 | $0.00014 | $0.00123 |
| Sonnet 5.5 | $0.00007 | $0.00061 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
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 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.
What it actually says
Ran Design
Use the host's product goals, framework and visual language. This skill needs no npm package.
Start with the design index and read only the owner relevant to the task. For a small correction, keep the scope small. For a redesign, establish real content, primary tasks, shared proportions and interaction states before decoration. Before implementation, record the style brief in the existing task note; update that brief before changing direction. Compare composed screens before adding motion.
Avoid unnecessary secondary labels and descriptions. Let the layout do the explaining. Preserve accessible names, useful constraints, errors and consequences.
Use screenshots of the actual host to inspect layout, content density and responsive states. Use continuous recordings for changed transitions, streaming, navigation and interruption. Record the source/runtime being inspected, observations and limits; fixtures do not certify another product. Distinguish automated checks, agent visual review and human acceptance. Do not add a confirmation step to work that is already authorized; the host project's own approval rules still apply.
When the project uses ranui or ranuts, load that library's sibling skill for installed-version contracts. These design references describe methods, not APIs or permission to install or upgrade dependencies.
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.
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 Changed b21bdff017c2
- yesterday First seen · 27 lines · 35 tokens per session scan A 4a3ccfb44edf
design is a skill published in the GitHub repository chaxus/ran (269 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 307 once invoked, about $0.0001 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 2026-10-25.
Other skills, from other repositories
elements
Use this skill by default for any UI-related work or with NVIDIA Elements (nve-), including creating, editing, reviewing, or debugging HTML, CSS, layout, theming, components, applications, prototypes, Claude Artifacts, Codex Sites pages, and standalone UI artifacts.
frontend-ui-engineering
Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
frontend-design
Design UI components, layouts, and responsive interfaces with accessibility.
ui-styling
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns…
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).…
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…