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 rojim666/SztuCode --skill uicraftgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/uicraft)<a href="https://agentmods.dev/skills/rojim666/sztucode/uicraft"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/uicraft/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/rojim666/sztucode/uicraft"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/uicraft.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 | $0.00152 | $0.02073 |
| Opus 5 | $0.00076 | $0.01037 |
| Sonnet 5 | $0.00030 | $0.00415 |
| Haiku 4.5 | $0.00015 | $0.00207 |
Grade A, and why
uicraft 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UICraft
Create interfaces with a clear design point of view while preserving usability, accessibility, performance, and the project's existing constraints.
Decision priority
Apply guidance in this order:
- Follow explicit user requirements and product constraints.
- Preserve the established brand and design system unless the user asks to change them.
- Protect task completion, accessibility, content clarity, and performance.
- Apply UICraft's aesthetic defaults only after the first three priorities are satisfied.
Treat the recommendations in this skill as context-sensitive defaults, not universal style laws.
Establish design context
Before making high-impact visual decisions, establish:
- target audience and usage context;
- primary jobs and critical user flows;
- brand personality and desired emotional tone;
- technical, accessibility, performance, and browser constraints.
Use context in this order:
- Use a
Design Contextsupplied by the user. - Read
.uicraft.mdfrom the project root when it exists. - Inspect README files, design tokens, existing components, and brand assets for explicit evidence.
- For missing high-impact product or brand information, ask a focused question. For low-risk gaps, state a conservative assumption and continue.
Infer technical constraints and existing patterns from code. Do not invent audiences, brand values, business goals, or user needs from implementation details alone. For first-time setup, read uicraft-init.md.
Execute a verified UI workflow
For implementation tasks:
- Inspect the relevant code, framework, reusable components, tokens, and existing tests.
- Run or preview the current interface when practical and capture a baseline before substantial visual changes.
- Select one primary workflow reference and only the supporting foundation references needed for the task.
- Implement the smallest coherent change that fulfills the request. Preserve existing conventions unless changing them is part of the goal.
- Verify behavior, visual output, responsive states, keyboard access, reduced motion, loading/error/empty states, and relevant tests.
- Preview the result after implementation and iterate when the visual result differs from the intended design.
- Report what changed, what was verified, and any remaining assumptions or untested conditions.
What ships with it
34 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.
- agents/openai.yaml 237 B
- LICENSE 11 KB
- references/adapt.md 7.6 KB
- references/animate.md 8.5 KB
- references/arrange.md 8.9 KB
- references/audit.md 8.3 KB
- references/bolder.md 7.4 KB
- references/clarify.md 8.0 KB
- references/cognitive-load.md 5.7 KB
- references/color-and-contrast.md 6.2 KB
- references/colorize.md 7.8 KB
- references/critique.md 12 KB
- references/delight.md 11 KB
- references/distill.md 7.0 KB
- references/extract.md 4.5 KB
- references/harden.md 11 KB
- references/heuristics-scoring.md 9.8 KB
- references/interaction-design.md 9.1 KB
- references/landing-page.md 8.8 KB
- references/motion-design.md 9.2 KB
- references/normalize.md 4.6 KB
- references/onboard.md 9.3 KB
- references/optimize.md 9.4 KB
- references/overdrive.md 10 KB
- references/personas.md 8.2 KB
- references/polish.md 9.5 KB
- references/portfolio.md 8.9 KB
- references/quieter.md 5.3 KB
- references/responsive-design.md 4.5 KB
- references/spatial-design.md 4.7 KB
- references/typeset.md 6.4 KB
- references/typography.md 7.0 KB
- references/uicraft-init.md 3.1 KB
- references/ux-writing.md 5.7 KB
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 · 151 lines · 152 tokens per session scan A 512a98595d2a
uicraft is a skill published in the GitHub repository rojim666/SztuCode (63 stars, last pushed 2d ago), licensed MIT. It adds 152 tokens to every session and 2,073 once invoked, about $0.0008 per session on Opus 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 2026-09-07.
Other skills, from other repositories
frontend-design
Use this skill for work a user will see rendered: websites, landing pages, dashboards, web applications, interface components, style overhauls, and requests to make an interface look better. It classifies the surface as expressive, conventional, or governed by an existing design system, then commits to palette…
design-system
DESIGN.md integration for Forge — ensures visual consistency across all UI tasks through standardized design specifications.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
high-end-visual-design
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.