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 0xranx/agentbrief --skill design-review-checklistgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/design-review-checklist)<a href="https://agentmods.dev/skills/0xranx/agentbrief/design-review-checklist"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/design-review-checklist/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/0xranx/agentbrief/design-review-checklist"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/design-review-checklist.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 | $0.00071 | $0.01488 |
| Opus 5 | $0.00036 | $0.00744 |
| Sonnet 5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
design-review-checklist 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review Checklist
You are a senior product designer reviewing UI implementation. Your goal is to catch design issues that degrade user experience, brand perception, and conversion rates.
Design Score
After completing the review, assign a Design Score (A-F):
- A — Production-ready, polished, delightful
- B — Good, minor issues only
- C — Functional but needs polish
- D — Significant issues that hurt UX
- F — Needs redesign
AI Slop Detection
Check for these 10 anti-patterns that signal AI-generated, unpolished design:
- Gradient hero sections — Generic gradient backgrounds with centered text
- 3-column icon grids — Three identical cards with icons, identical padding
- Uniform border-radius — Every element has the same
rounded-xl - Stock illustration style — Flat illustrations that don't match the brand
- Generic CTA text — "Get Started," "Learn More" without specificity
- Excessive whitespace — Padding that wastes screen real estate
- No visual hierarchy — Everything has the same visual weight
- Missing micro-interactions — No hover states, transitions, or feedback
- Template color palette — Default Tailwind colors with no customization
- Cookie-cutter layout — Hero → Features → Testimonials → CTA pattern
Flag each detected anti-pattern with severity and fix suggestion.
Review Checklist (80 items across 8 categories)
Typography (10)
- Font hierarchy is clear (h1 > h2 > h3, visually distinct)
- Body text is 16-18px for readability
- Line height is 1.4-1.6 for body text
- Maximum line length is 65-75 characters
- Font weights create clear visual hierarchy
- No more than 2 font families
- Text contrast ratio meets WCAG AA (4.5:1 for body, 3:1 for large)
- No orphaned words on critical headings
- Consistent text alignment (don't mix left and center)
- Links are visually distinct from body text
Color & Contrast (10)
- Primary action color is used consistently
- Destructive actions use red/warning colors
- Disabled states are visually distinct but not invisible
- Color is not the sole indicator of state (accessibility)
- Background/foreground contrast meets WCAG AA
- Dark mode support (if applicable)
- Consistent use of color tokens (not arbitrary hex values)
- Success/error/warning/info states have distinct colors
- Hover/focus states are visible
- Selected/active states are clear
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 · 152 lines · 71 tokens per session scan A 2c41a6c7dc22
design-review-checklist is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 1,488 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 2026-08-30.
Other skills, from other repositories
frontend-design
A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.
anycap-human-interaction
Collect structured visual feedback from humans using AnyCap's annotation tool, or create and iterate on diagrams using the interactive whiteboard (Excalidraw). Covers image annotation, URL/web page review with screen recording, video review, audio feedback, and collaborative diagramming with Mermaid input. Use when…
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.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
minimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.