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-analysegit 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-analyse)<a href="https://agentmods.dev/skills/madappgang/magus/ui-analyse"><img src="https://agentmods.dev/badge/skills/madappgang/magus/ui-analyse/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-analyse"><img src="https://agentmods.dev/badge/skills/madappgang/magus/ui-analyse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.02741 |
| Opus 5 | $0.00024 | $0.01371 |
| Sonnet 5 | $0.00010 | $0.00548 |
| Haiku 4.5 | $0.00005 | $0.00274 |
Grade A, and why
ui-analyse 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 9d 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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Analysis Skill
Overview
Patterns, checklists and templates for reviewing a UI visually. Analysis only —
to implement the improvements, use dev:frontend-implement.
Getting the Image In Front of You
Read("screenshots/dashboard.png")
That is the whole mechanism. Claude Code renders a .png/.jpg into context as an
image, so you review the screen rather than its filename. You are the vision
model. There is no model to select, no catalog lookup, no API key, no encoding
step, and no "vision unavailable" fallback.
Read one image per call. Call it twice to hold a reference and an implementation side by side — reference first, so "Image 1" and "Image 2" mean what the prompt says.
There is no CLI path for handing claudish an image. claudish has no --image flag,
and unknown flags pass straight through to claude, which has none either. An
[Image: data:image/png;base64,…] or [Image: https://…] reference typed into a prompt is
plain text — nothing decodes it, nothing fetches it. Either route returns a fluent,
confident review of a screen the model never saw, and reports no error while doing it.
Claudish can carry images — it converts image blocks to image_url for the provider, and
describes them via a vision proxy when the target model has no vision of its own. That path
runs through a session (see "A Second Opinion" below), where the spawned Claude Code
Reads the file.
When to Use
- Reviewing screenshots, wireframes, or mockups
- Conducting accessibility audits
- Validating design system consistency
- Comparing an implementation against its design reference
- Analysing UI patterns and usability
Relationship to Other Skills
| Skill | Purpose | Modifies Code? |
|---|---|---|
| designer:ui-analyse | Visual analysis, issue detection | No |
| dev:frontend-implement | Apply improvements from analysis | Yes |
| designer:ui-style-format | Style file specification | No |
| designer:design-references | Reference image management | No |
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.
- 9d ago First seen · 326 lines · 48 tokens per session scan A 80056028be5c
ui-analyse is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 2,741 once invoked, about $0.0002 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 2026-08-31.
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.