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 skillmds/skillmd --skill snowe-ui-skillgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/snowe-ui-skill)<a href="https://agentmods.dev/skills/skillmds/skillmd/snowe-ui-skill"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/snowe-ui-skill/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/skillmds/skillmd/snowe-ui-skill"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/snowe-ui-skill.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 | $0.00057 | $0.00688 |
| Opus 5.5 | $0.00023 | $0.00275 |
| Sonnet 5.5 | $0.00011 | $0.00138 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
Snowe UI 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 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snowe UI Skill
Snowe is an architecture-first UI/UX design skill for Codex and compatible SKILL.md runtimes.
Use it when a coding agent needs to design, redesign, implement, or critically review a web, mobile, or desktop product without jumping directly from a brief into a familiar layout, visual style, or landing-page recipe.
Snowe works from product truth and the actual user journey, keeps high-leverage design decisions open until evidence closes them, compares materially different experience directions, and records important choices causally:
driver → design move → expected consequence → evidence → risk → revisit trigger
The skill covers experience architecture, navigation, information hierarchy, art direction, typography, color and materials, imagery, iconography, custom graphics, motion, interaction, accessibility, responsive transformation, implementation, and rendered browser evaluation.
Snowe explicitly allows outcomes such as no imagery, no custom asset, or no animation when those choices better serve the product. Local evidence can support discovery and comparison, but it does not classify the brief or define the allowable solution space.
Snowe is not a category-to-style generator or a landing-page recipe system. Its goal is to help coding agents produce more product-specific interfaces while preserving strong existing decisions and revising weak ones through rendered evidence.
Installation
No source-backed install or usage instructions could be extracted automatically. Review the upstream project before running this skill in a sensitive workflow.
Usage
Invoke Snowe from a real design or implementation task.
For an existing product:
Use $snowe-ui-skill to review this existing product, preserve what works, and improve the most consequential UX and visual-quality failures.
For a new experience:
Use $snowe-ui-skill to design and build this product from product truth through rendered QA.
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 · 71 lines · 57 tokens per session scan A 2a4944016e2a
Snowe UI Skill is a skill published in the GitHub repository skillmds/skillmd (143 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 688 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 2026-09-19.
Snowe UI Skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Snowe UI Skillskillmds/skillmd | Skill | 143 | 4d ago | MIT | A | 57 | Claude Code |
| frontendcode-yeongyu/lazycodex | Skill | 3.9k | yesterday | MIT | A | 79 | Codex |
| designlang-tokensManavarya09/design-extract | Skill | 4.8k | 2d ago | MIT | A | 30 | Claude Code |
| cli-anything-photoshopyb2460/harness-anything | Skill | 3.0k | 29d ago | MIT | A | 43 | Claude Code, Codex |
| app-screenshot-debugtermio-sh/termio | Skill | 785 | 5d ago | MIT | A | 161 | Claude Code, Codex |
| user-research-cookiycookiy-ai/user-research-skill | Skill | 1.6k | 5d ago | MIT | A | 154 | Claude Code, Codex |
| write-zot-themespatriceckhart/zot | Skill | 360 | yesterday | MIT | A | 23 | Claude Code, Codex |