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/getcrew44/crew44/design-critiquenpx skills add getcrew44/crew44 --skill design-critiquegit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/design-critique)<a href="https://agentmods.dev/skills/getcrew44/crew44/design-critique"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/design-critique.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 5.1 | $0.00037 | $0.00631 |
| Opus 5 | $0.00018 | $0.00316 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Critique
Give the kind of feedback a designer actually wants: specific, prioritized, and tied to the user's goal — not adjectives.
Frame the critique
Ask, then critique. The same screen gets different feedback at different stages.
- Stage. Exploration (push for range), refinement (tighten), or polish (catch what shipped).
- Context. Who is it for? What is the user trying to do? What is this screen in service of?
- Focus. All of it, or one slice (navigation, the empty state, the hero, the form)?
Pass 1: First impression (two seconds)
- What draws the eye first? Is that what should?
- Is the purpose of the screen clear before you read any copy?
- What's the emotional read — calm, urgent, dense, sparse — and does that match the user's state?
Pass 2: Hierarchy and reading flow
- Does the reading order match what the user is trying to do?
- Are the right elements emphasized? Anything competing with the primary action?
- Is whitespace doing work, or just sitting there?
Pass 3: Usability
- Can the user accomplish the goal without backtracking?
- Are interactive elements obviously interactive? Are read-only elements clearly not?
- Are there unnecessary steps, fields, or confirmations?
Pass 4: Consistency
- Does this match the existing design system, or invent locally? Name the specific deviations.
- Spacing, typography, color tokens — pulled from the system, or magic numbers?
- Do similar elements behave similarly across the screen?
Pass 5: Accessibility floor
- Color contrast: body text ≥ 4.5:1, large text and UI ≥ 3:1.
- Touch targets ≥ 44×44.
- Focus order is logical; focus indicators are visible.
- Form inputs have labels, not just placeholders.
How to deliver feedback
- Be specific. "The CTA competes with the navigation" beats "the layout is confusing."
- Explain the why. Tie each note to a user need or principle, not just taste.
- Suggest, don't just diagnose. A direction is more useful than a problem.
- Call out what works. Reinforces the moves to keep.
- Rank by impact. Lead with the change that buys the most.
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.
- 6d ago First seen · 63 lines · 37 tokens per session scan A a9d236f5a4ec
design-critique is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 631 once invoked, about $0.0002 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
visualize
Create visualizations and interactive tools directly in conversation. Use when asked to show how something works, make simulators or labs, maps, plots, charts or graphs, comparisons, UI mockups, scenarios, adjustable inputs, and exploration beyond regular text.
brand-visual-quality
品牌视觉资产生产质量 Owner — 当任务涉及品牌标志、图标、主题变体、微尺寸光学校正、单色母版、主资产谱系或视觉验收证据时使用；要求把几何一致性、变体关系和人工视觉结论绑定到可重放证据，避免只凭文件存在或单次截图宣告完成。.
design-system-architecture
设计系统架构专家 Owner — 当任务涉及设计系统、主题、Token、组件变体、Figma/代码同步、UI 一致性、可访问性、国际化、品牌视觉或组件库治理时使用；要求把视觉规则沉淀为可复用、可验证的系统契约。.
ux-interaction-architecture
UX 交互架构专家 Owner — 当任务涉及页面流程、信息架构、任务路径、交互状态、空/错/加载/恢复、可理解性、操作成本、键盘/无障碍触点或用户要求补充交互设计规范时使用；要求从用户任务和状态反馈闭环审查体验。.
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.
clone-website
Reverse-engineer and clone one or more websites in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases…