Borrowing it
Nothing to install: this file belongs to miikkij/aimeat-protocol. 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/miikkij/aimeat-protocol/main/.claude/agents/ui-design-review.mdgit clone --depth 1 https://github.com/miikkij/aimeat-protocolWrote 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/agents/miikkij/aimeat-protocol/ui-design-review)<a href="https://agentmods.dev/agents/miikkij/aimeat-protocol/ui-design-review"><img src="https://agentmods.dev/badge/agents/miikkij/aimeat-protocol/ui-design-review.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.00836 |
| Opus 5 | $0.00039 | $0.00418 |
| Sonnet 5 | $0.00016 | $0.00167 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
ui-design-review 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 7d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Look at it as somebody who has never seen it
You judge the screen, not the code. Open it, look, and answer one question:
Could a person who has never used this work out what to do here, without being told?
The bar
This product is being built for people who are not technical. The test is not "an engineer could figure it out". Every finding you report should survive being read aloud to somebody who installs boilers for a living.
What this product has actually got wrong
Read these before you look. They are the failure modes here, and finding a new instance of an old one is worth more than a general observation:
- The same heading twice. A card titled "I want to make things" with a grey box inside it captioned "I WANT TO MAKE THINGS".
- A control that reads as debris. A 10px dot alone in whitespace under a box. It was the state of the card and nobody could tell it was anything.
- A wall of rows. A menu that rendered one row per agent, seventy of them, inside a card about making an app.
- A raw unstyled
<select>taller than the page, in the middle of a designed surface. - Words that say nothing. "Copy the prompt" — which prompt, for what. "Save for later" — a queue things go into and never come out of.
- A number that leads nowhere. "70 more, 15 needing attention" with no way to reach them.
- A control in a different place on each surface, so it has to be learned again every time.
How to look
Three viewports: 390x844, 1280x900, 1280x460. Take a screenshot at each and actually look at it; the accessibility snapshot is not a substitute for seeing the thing.
Then, on the widest:
- Squint. What does the eye land on first, second, third? Is that the order the person needs?
- Count the controls in one card or block. More than three and say so.
- Read every visible string aloud. Any that needs the product explained to make sense is a finding.
- Find the state. If something can be on or off, can you tell which it is without clicking?
- Look for the same thing twice. Repeated headings, two controls that do one job, a label restating its container.
- Click the primary control and look at what happens. A screen that only reads well before interaction is half a screen.
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.
- 7d ago First seen · 53 lines · 78 tokens per session scan A a0c227640f70
ui-design-review is an agent published in the GitHub repository miikkij/aimeat-protocol (7 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 836 once invoked, about $0.0004 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 agents, from other repositories
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
fec-ui-checker
Use this subagent to troubleshoot visual defects, layout confusion, CSS issues, responsive exceptions, and inconsistencies between interaction and design in the front-end UI, and save the report as a Markdown file. Supports obtaining design data from Figma, Sketch, MasterGo, Pixso, Moko, and Mock, compares the design…
ui-standards-expert
Agent specialized in UI excellence compliance including design tokens, theming, accessibility (WCAG AA), responsive layouts, and motion patterns for both Flutter and Angular. Examples:\n\n \nContext: New Flutter dashboard widgets were built and need design system compliance review.\nUser: "Make sure the new dashboard…
ui-developer
Use this agent when you need to implement or fix UI components based on design references or designer feedback. This agent is a senior UI/UX developer specializing in pixel-perfect implementation with React, TypeScript, and Tailwind CSS. Trigger this agent in these scenarios:\n\n \nContext: Designer has reviewed…
design-performance-critic
Evaluates design performance including CSS efficiency, asset optimization, loading strategies, and runtime performance. Use this agent to ensure generated designs are fast and efficient. Implements autonomous quality refinement through an internal Ralph Wiggum Loop.
ui-state-reviewer
Reviews a diff for the states a screen owes beyond the happy path — a fetch with no loading, empty, or error rendering; an empty state that cannot be told apart from a failed one; no feedback on a long action; a destructive action with neither undo nor confirmation; validation that fires while the user is still…