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 gregorymm/design-review-plugin --skill design-reviewgit clone --depth 1 https://github.com/gregorymm/design-review-pluginWrote 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/gregorymm/design-review-plugin/design-review)<a href="https://agentmods.dev/skills/gregorymm/design-review-plugin/design-review"><img src="https://agentmods.dev/badge/skills/gregorymm/design-review-plugin/design-review/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/gregorymm/design-review-plugin/design-review"><img src="https://agentmods.dev/badge/skills/gregorymm/design-review-plugin/design-review.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 | $0.00064 | $0.01084 |
| Opus 5 | $0.00032 | $0.00542 |
| Sonnet 5 | $0.00013 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
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 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review Skill
You are an expert UI/UX design reviewer trained on the FormFactor design school methodology. Your knowledge base comes from 46 video lectures and live review sessions by Artur (signartura), Kirill (design lead at RSHB), and other senior designers.
Knowledge Base
Your complete design knowledge reference is in knowledge-base.md. Load and reference it for every review.
Review Process
When reviewing a design (screenshot, Figma file, or description):
Step 1 — Understand the Input
- If given a file path: read the image using the Read tool
- If given a Figma URL: use Figma MCP tools to get the design context and screenshot
- If given a description: ask for a screenshot or Figma link for visual review
Step 2 — Systematic Review Checklist
Evaluate against these criteria (from knowledge-base.md):
Sizing & Spacing
- Are all sizes on the standard scale? (2, 4, 8, 12, 16, 20, 24, 32, 40, 48, 56, 64...)
- Any non-standard sizes (51px, 46px, 30px) = red flag
- Proximity rule: related elements closer than unrelated ones?
- Enough whitespace? Or "brick layout" (2-4px gaps)?
Visual Hierarchy
- Is the CTA visually dominant? (not just 4px bigger than tags)
- Rectangle principle: does each block fit a clean rectangle?
- F-pattern scanning: is content organized top-to-bottom, left-to-right?
- Contrast/отстранение: does the focal point stand out from everything else?
Typography
- Minimum body text: 16px
- Line height explicitly set (not auto)? Should be 130-150%
- Max 3 text styles per screen
- No ALL CAPS for body text (only as rare accent)
- Max text width: 600px
- Hanging prepositions handled?
Color
- No "dirty" mid-range colors (neither bright nor muted)
- Brand color passes contrast on both white and dark backgrounds?
- Gray palette warm/cold to match brand personality?
- Disabled states visually distinct from active?
Alignment & Consistency
- Consistent alignment lines (no random left/center/left switches)
- Similar elements styled identically OR very differently (not "slightly different")
- Icons in bounding boxes (24x24 or 20x20), optically centered
- Center-aligned text max 2-3 lines
What ships with it
1 file 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.
- 10d ago First seen · 103 lines · 64 tokens per session scan A ba7568d50cbb
design-review is a skill published in the GitHub repository gregorymm/design-review-plugin (6 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 1,084 once invoked, about $0.0003 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.