Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/ui-design-reviewer/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/ui-design-reviewer)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/ui-design-reviewer"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/ui-design-reviewer/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/greenmtnsun/giteasy/ui-design-reviewer"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/ui-design-reviewer.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 | $0.00205 | $0.02444 |
| Opus 5.5 | $0.00082 | $0.00978 |
| Sonnet 5.5 | $0.00041 | $0.00489 |
| Haiku 4.5 | $0.00020 | $0.00244 |
Grade A, and why
ui-design-reviewer scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
or a test plan relies on. Request each web address (`curl -s -o /dev/null -w '%{http_code}' -L`), 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 design reviewer
You review a screen design the way a careful accessibility and interaction reviewer would, and you
report findings a builder can act on. You don't redesign and you don't repair. In a review loop you
are a fresh agent each round (see the review-loop skill), and the builder fixes what you report.
This skill comes from the first real run of the UI design review loop, on WikiMint's repository form on 2026-11-14. That run went five rounds and made 22 findings, and the examples marked "Trial" below are from it. They show the kind of thing to look for. They aren't evidence about the design in front of you, so leave them out of your findings. A builder on another project can't act on "the same mismatch the trial found."
What to gather before judging
Read the source, not only the pictures. A mockup's HTML or XAML carries the notes, component names and states that a PNG hides.
- The mockups: their source file and every captured image of a state you comment on. If you skip images, say which ones in your notes.
- The design decision record (DR) and any state diagram for the screens.
- The product's component reference, from the real source:
- Forge and Confluence apps: the forge MCP tools
get-ui-kit-component-reference,list-ui-kit-componentsandatlassian-design-tokens. - DetentShell: its theme and control styles in the PS7-ISE repo, plus its current screens.
- Websites: the site's own CSS tokens and existing pages.
- Forge and Confluence apps: the forge MCP tools
- Screens Keith has already approved, and his rulings on this design. Something he ruled out (a screen, a toggle, a line of text) being absent is correct, not a gap.
- The product's existing screens, so the new design matches conventions already shipped.
- Anything else that depends on these screens: a test plan or checklist for them, and the project's ledger for what is already built or deployed.
How to look
Check things by measuring them, not by eye. Each technique below caught a real finding.
What ships with it
4 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.
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.
- today First seen · 180 lines · 205 tokens per session scan A 4415d2359168
ui-design-reviewer is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 205 tokens to every session and 2,444 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-18.
ui-design-reviewer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ui-design-reviewergreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 205 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 108k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | yesterday | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 11k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | today | MIT | A | 47 | Claude Code |