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 MadAppGang/magus --skill ui-style-formatgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/ui-style-format)<a href="https://agentmods.dev/skills/madappgang/magus/ui-style-format"><img src="https://agentmods.dev/badge/skills/madappgang/magus/ui-style-format/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/madappgang/magus/ui-style-format"><img src="https://agentmods.dev/badge/skills/madappgang/magus/ui-style-format.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 | $0.00041 | $0.01070 |
| Opus 5 | $0.00020 | $0.00535 |
| Sonnet 5 | $0.00008 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
ui-style-format 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 10d 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.
This is a copy
91% identical to ui-style-format — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Style Format Specification
Overview
The UI Style system provides a standardized way to define project design preferences
that the ui agent uses during design reviews. It supports both text-based style
definitions and visual reference images.
File Structure
{project}/
.claude/
design-style.md # Main style configuration
design-references/ # Visual reference images
{image}.png # PNG or JPG screenshots
MANIFEST.md # Optional metadata
design-style.md Schema
Required Sections
| Section | Purpose |
|---|---|
| Header | Version, dates, base reference |
| Reference Images | Links to visual references (v2.0+) |
| Brand Colors | Color palette with light/dark modes |
| Typography | Fonts and type scale |
| Spacing | Base unit and scale |
| Component Patterns | Button, input, card styles |
| Design Rules | DO and DON'T guidelines |
Optional Sections
| Section | Purpose |
|---|---|
| Reference URLs | External style guides |
| Style History | Change log |
| MANIFEST.md | Detailed image descriptions |
Reference Images Integration
Storage Location
All reference images MUST be stored in .claude/design-references/.
Supported Formats
| Format | Extension | Recommended Use |
|---|---|---|
| PNG | .png | Screenshots, UI components |
| JPEG | .jpg, .jpeg | Photos, complex imagery |
| WebP | .webp | Modern alternative to PNG/JPEG |
Image Table Format
In the style file, reference images are listed in a table:
## Reference Images
| Image | Description | Captured | Mode |
|-------|-------------|----------|------|
| hero-section.png | Homepage hero | 2026-01-08 | light |
Usage Guidelines Section
Each image should have usage notes:
### Usage Guidelines
- **hero-section.png**: Reference for hero layout, gradient, CTA placement
Parsing the Style File
Section Extraction
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.
- 10d ago First seen · 180 lines · 41 tokens per session scan A 61dd4528a1cf
ui-style-format is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 1,070 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to ui-style-format, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.