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 agentmods add skills/random6913/claude-code-superkit/visual-reviewernpx skills add RaNDoM6913/claude-code-superkit --skill visual-reviewergit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWrote 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/random6913/claude-code-superkit/visual-reviewer)<a href="https://agentmods.dev/skills/random6913/claude-code-superkit/visual-reviewer"><img src="https://agentmods.dev/badge/skills/random6913/claude-code-superkit/visual-reviewer.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 | $0.00021 | $0.00744 |
| Opus 5 | $0.00010 | $0.00372 |
| Sonnet 5 | $0.00004 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
visual-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Reviewer
Compare UI screenshots before/after changes. Score visual consistency 0-100. Pass threshold: 90+.
Phase 0: Load Project Context
Read if exists:
AGENTS.md— design system, UI conventions.codex/skills/project-architecture/SKILL.md— UI components, styling approach- Frontend config files (tailwind.config, theme files)
When to Use
- After frontend component changes in dev-orchestrator pipeline
- When touching CSS/styling files
- Before UI-heavy PR merges
- Design system migration validation
Process
Step 1: Identify Visual Changes
git diff --name-only | grep -E '\.(tsx|jsx|vue|svelte|css|scss|less|html)$'
If no visual files changed, skip and report "No visual changes detected."
Step 2: Check for Screenshots
Look for screenshots in common locations:
/tmp/screenshots/tests/screenshots/- User-provided paths
If no screenshots available, perform code-only visual review (Step 3 alternative).
Step 3: Code-Based Visual Review
When screenshots are unavailable, review code for visual consistency:
- Color consistency — are colors from the design system/theme, not hardcoded hex?
- Spacing consistency — are spacing values from the scale (4px/8px/12px/16px/24px/32px)?
- Typography — are font sizes/weights from the type scale?
- Z-index — are z-index values from a defined scale, not arbitrary numbers?
- Responsive — are breakpoints using the defined set?
- Animation — are transitions using the project's animation library/conventions?
- Accessibility — are interactive elements focusable? Alt text on images? Aria labels?
- Dark mode — if the project supports it, are new elements themed correctly?
Step 4: Score
| Check | Weight | Pass Criteria |
|---|---|---|
| Color system compliance | 15 | All colors from theme/design tokens |
| Spacing scale compliance | 15 | All spacing from defined scale |
| Typography compliance | 10 | Font sizes/weights from type scale |
| Z-index discipline | 10 | Values from defined scale |
| Responsive correctness | 15 | All breakpoints covered |
| Animation consistency | 10 | Uses project animation library |
| Accessibility | 15 | Focusable, labeled, contrast OK |
| Dark mode (if applicable) | 10 | Themed correctly |
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.
- yesterday First seen · 95 lines · 21 tokens per session scan A bb409f5fb19b
visual-reviewer is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 744 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
devx-ux
Activate when designing or modifying CLI command surfaces, command help text, install/init/run flows, error wording, or first-run experience in the APM CLI -- even when the user does not say "UX" explicitly.
core-components
Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
frontend-specialist
前端开发专家。用于前端应用、页面、组件、现有 UI 增量改进、已有页面视觉优化、UI/UX 改造、视觉重设计、响应式布局、表单和输入框视觉一致性、设计系统落地、React/Vue/Next.js/Nuxt、Tailwind、shadcn/ui、Radix、MUI、AntD、仪表盘、SaaS、Landing Page、移动端适配、前端性能优化、浏览器截图检查和去除 AI 味 UI。触发后应把“做好看”转化为可执行设计约束，优先复用项目现有组件与视觉语言，小步实现并尽量通过浏览器或 Playwright 做视觉反馈闭环；当用户要改进当前页面或已有界面时，默认先诊断再做局部优化，而不是从 0 重做。.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…