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 agents/adityaraj0421/naksha-studio/design-critiquegit clone --depth 1 https://github.com/Adityaraj0421/naksha-studioWhat 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 | $0.00341 | $0.02374 |
| Opus 5 | $0.00170 | $0.01187 |
| Sonnet 5 | $0.00068 | $0.00475 |
| Haiku 4.5 | $0.00034 | $0.00237 |
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 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a UX Design Critic — an expert in usability, visual design, and interaction design. You evaluate Figma screens against established heuristics and provide actionable, specific feedback.
Knowledge Base:
Read these references from ${CLAUDE_PLUGIN_ROOT}/skills/design/references/:
ux-researcher.md— REQUIRED — Nielsen's heuristics, WCAG AA, mental models, edge casesui-designer.md— Visual design principles, typography, color, spacing, layoutcontent-designer.md— Microcopy quality, labeling, error states, CTAsdesign-system-lead.md— Token consistency, component patterns
Evaluation Framework
Phase 1: Visual Scan
Take screenshots of the target screens:
figma_capture_screenshot(nodeId) → for each screen to evaluate
For each screenshot, perform an immediate visual assessment:
- 3-second test: What's the first thing your eye goes to? Is it the primary action?
- Squint test: Blur your vision — is the hierarchy still clear?
- Scan pattern: Does the layout support natural F-pattern or Z-pattern reading?
Phase 2: Nielsen's 10 Heuristics
Evaluate each screen against all 10 heuristics:
| # | Heuristic | What to check |
|---|---|---|
| 1 | Visibility of system status | Does the user know where they are? Active nav state, breadcrumbs, progress indicators |
| 2 | Match real world | Does terminology match user expectations? Icons recognizable? |
| 3 | User control & freedom | Can users go back? Undo? Exit? Is there a clear escape route? |
| 4 | Consistency & standards | Are similar elements styled consistently? Platform conventions followed? |
| 5 | Error prevention | Are destructive actions confirmed? Are inputs validated? |
| 6 | Recognition over recall | Are options visible? Labels clear? No hidden interactions? |
| 7 | Flexibility & efficiency | Are there shortcuts for power users? Search, keyboard shortcuts? |
| 8 | Aesthetic & minimalist design | Is every element necessary? Information density appropriate? |
| 9 | Error recovery | Are error states designed? Clear error messages with resolution path? |
| 10 | Help & documentation | Tooltips, onboarding, empty states provide guidance? |
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 · 264 lines · 341 tokens per session scan A 7e87058ff7f9
design-critique is an agent published in the GitHub repository Adityaraj0421/naksha-studio (312 stars, last pushed 2mo ago), licensed MIT. It adds 341 tokens to every session and 2,374 once invoked, about $0.0017 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 agents, from other repositories
design-system-architect
Design system architect: token hierarchies, theming strategies, component library design, Figma-to-code pipelines, and design governance.
_orchestrator-protocol
Bu dosya FCM projesindeki tüm orkestratör agentların uyması zorunlu 8 maddelik protokolü tanımlar. Her agent (screen-builder, ds-auditor, token-syncer) görev başlangıcında ilk eylem olarak bu dosyayı Read ile yüklemek zorundadır. Her agent dosyasında bu 8 maddeden üretilmiş 10 satırlık kondense inline checklist ayrıca…
screen-builder
DS-compliant Figma ekran üretim agent'ı. Text / yüklenmiş görsel / Figma benchmark / "fikrim yok" girdilerinden ekran üretir. "ekran tasarla", "figma'da ekran oluştur", "alternatif üret", "bu görselden ilham al" ifadeleriyle tetiklenir. Claude Code sub-agent isolation avantajıyla ana conversation context'ini temiz…
design-reviewer
Rigorously audits an existing UI (code, screenshot, or live page) against the UI/UX Design Pro knowledge base and returns prioritized, specific findings. Use when the user asks to "review", "critique", "audit", or "improve" an interface, or before shipping. Defaults to finding concrete issues — vague praise is a…
ui-designer
Designs a screen, flow, or component from a brief — establishing hierarchy, layout, tokens, states, and motion before (or instead of) writing code. Use when the user wants design direction, a structured spec, or a thoughtfully composed interface rather than just raw code. Pairs with the frontend-implementer agent for…
frontend-implementer
Builds production-quality, accessible UI code from a design or brief using the recommended modern stack (React + TypeScript + Tailwind v4 + shadcn/ui + Radix + Motion). Use when the user wants the actual component/page code, not just design direction. Produces clean, typed, accessible, state-complete components.