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 Laith0003/ux-skill --skill ux-skill-foundationsgit clone --depth 1 https://github.com/Laith0003/ux-skillWrote 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/laith0003/ux-skill/ux-skill-foundations)<a href="https://agentmods.dev/skills/laith0003/ux-skill/ux-skill-foundations"><img src="https://agentmods.dev/badge/skills/laith0003/ux-skill/ux-skill-foundations/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/laith0003/ux-skill/ux-skill-foundations"><img src="https://agentmods.dev/badge/skills/laith0003/ux-skill/ux-skill-foundations.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 | $0.00083 | $0.01262 |
| Opus 5.5 | $0.00033 | $0.00505 |
| Sonnet 5.5 | $0.00017 | $0.00252 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
ux-skill-foundations 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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ux-skill foundations in Figma
ux-skill builds a design system from a brand color and a brief (or reads one a team already has) and checks it before handing it over: every pairing is measured for contrast in light, dark and high contrast, and the build refuses to write a system that fails. This skill brings that system into a Figma file as variables with their modes, and builds components from ux-skill's contracts with every visual property bound to a variable. The code and the file then hold one system.
Prerequisites. The figma-use skill MUST be loaded for every use_figma call. ux-skill runs locally (pip install uxskill, Python 3.10 or newer); it never calls a model and needs no network.
1. Get the system
Pick one source, in this order:
- The team's own tokens. A DTCG tokens.json, a CSS file of custom properties, a Tailwind 4 theme, Markdown rule files or a Figma variables export. Read it as it is, never rebuilt:
uxskill system import --from <file>reports what it read and lists every entry it did not read with how to write it. An existing system is fixed input; extend it beside its source withuxskill system extend --from <file> --add <foundation> --out <folder>, never rewrite it. - A brand color and a brief.
uxskill system build --brand '#3366FF' --brief .ux/system-brief.json --out design-system. The look follows the brand and the brief's axes as continuous values, never a preset by industry. Readdesign-system/system-report.mdbefore going on: it says what was built and what the engine moved to pass contrast.
Stop and tell the user when the build reports a failure: nothing was written, and the message names the token and the change to make.
2. Variables
Export the variables and the script that applies them: uxskill system export --from design-system/tokens.json --to figma --out figma-export.
figma-variables.jsonholds one collection per foundation (color, type, space, layout, radius, border, elevation, motion, imagery), each with the modes it changes in: light and dark, standard and high contrast, comfortable and compact, left to right and right to left, full and reduced motion.figma-variables.jscreates or updates them in the open file. Run its text throughuse_figma. It matches by name, so a second run updates in place; it never deletes a variable or renames a mode it did not make.- Primitives are hidden and unscoped; roles alias them and carry the scope that binds them (fills, text, strokes, gaps, radii) and their web code syntax (
var(--color-action-primary)). - What Figma variables cannot hold is listed in the export's notes, for example a font family keeps its first face and the fallbacks stay in tokens.json.
What ships with it
1 file 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.
- 4d ago First seen · 55 lines · 83 tokens per session scan A e5882186f76d
ux-skill-foundations is a skill published in the GitHub repository Laith0003/ux-skill (96 stars, last pushed 4d ago), licensed MIT. It adds 83 tokens to every session and 1,262 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 2026-11-02.
ux-skill-foundations compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-skill-foundationsLaith0003/ux-skill | Skill | 96 | 4d ago | MIT | A | 83 | Claude Code |
| ai-image-frontend-uiqiuxinyuan321/fumeng | Skill | 2 | 6mo ago | MIT | A | 7 | Claude Code, Codex |
| Cognitive Load AnalyzerPramodDutta/qaskills | Skill | 245 | 3d ago | MIT | A | 29 | Claude Code, Codex |
| reimagine-it-lockKayforkind/reimagine-it | Skill | 212 | 5d ago | MIT | A | 108 | Claude Code |
| paintAThevon/genjutsu | Skill | 749 | 3d ago | none | A | 46 | Claude Code |
| compose-graphicsAThevon/genjutsu | Skill | 749 | 3d ago | none | A | 36 | Claude Code |
| desktop-principlesAThevon/genjutsu | Skill | 749 | 3d ago | none | A | 36 | Claude Code |