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 hamzaPixl/pixl-ai --skill design-critiquegit clone --depth 1 https://github.com/hamzaPixl/pixl-aiWrote 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/hamzapixl/pixl-ai/design-critique)<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/design-critique"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/design-critique/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/hamzapixl/pixl-ai/design-critique"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/design-critique.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 | $0.00077 | $0.01638 |
| Opus 5.5 | $0.00031 | $0.00655 |
| Sonnet 5.5 | $0.00015 | $0.00328 |
| Haiku 4.5 | $0.00008 | $0.00164 |
Grade A, and why
design-critique 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Independent, opinionated design review that evaluates UI against a catalog of anti-patterns and the "AI Slop Test" — the instinct to look generic, templated, or machine-generated. Produces a scored report (6 axes, 1-10) and a prioritized fix list. Critique only — use /design-polish to auto-fix findings or /design-distill to strip overdesign.
How this differs:
/react-doctor— code health (hooks, a11y, perf). This skill — visual craft and design quality./cto-review— architectural review. This skill — pixel-level aesthetics./design-variants— generate new directions. This skill — critique what already exists.
Required References
Before starting, read these design vocabulary files:
references/frontend/design/anti-patterns.md— banned patterns catalogreferences/frontend/design/craft-process.md— craft rubricreferences/frontend/design/typography.md— type scale, pairing, hierarchyreferences/frontend/design/color-and-contrast.md— palette, contrast, semantic color
Step 1: Identify Scope
Resolve what to critique:
- File path (
src/components/Hero.tsx) — read the component and its styles - Page URL (
http://localhost:3000/pricing) — use WebFetch to retrieve rendered HTML/CSS - Directory (
src/components/) — scan all components, pick top 5 by size/importance - No arg — look for a running dev server, critique the home page; else ask user
Gather:
- Design tokens (
tailwind.config.*,design-config.ts, CSS variables) .design-context.mdat project root (brand voice, audience, anti-references) if present- Screenshots from
.playwright-mcp/if the agent-browser has been used
Step 2: Scan for Banned Patterns
Grep the target files/HTML for known AI-slop tells:
| Pattern | Regex / signal |
|---|---|
| Gradient text | bg-clip-text.*gradient, background-clip: text with gradient |
| Default Inter everywhere | font-family.*Inter with no other font defined |
| Gray text on colored bg | text-gray-\d+ inside elements with non-neutral background |
| Side-stripe borders | border-l-4, colored left accent on cards |
| Emoji-as-icon | Emoji characters in headings, buttons, or feature lists |
| Centered hero + 3-card grid | Classic template layout with no deviation |
| Generic placeholder imagery | unsplash.com stock, placehold.co in production |
| Overused shadow scale | shadow-lg, shadow-xl on every card |
| Purple-to-pink gradient | Hardcoded #8B5CF6 to #EC4899 or similar AI defaults |
| Rounded-full on everything | Pills, avatars, and buttons all sharing the same radius |
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.
- 1mo ago First seen · 135 lines · 77 tokens per session scan A 4d1f2ae72f79
design-critique is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 1,638 once invoked, about $0.0003 per session on Opus 5.5. 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 $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.