A visual review guide for software interfaces, focused on layout, typography, usability, distinctiveness, and careful detail. It uses references such as Apple, Linear, Stripe, Vercel, and A24, with a dark-first approach when appropriate.

Use it to review new screens, interface changes, visual refactors, dark-mode designs, and products that include AI agents, checking clarity, polish, usability, and consistency.

It helps identify visual problems and weak user experiences before a new interface or redesign is released. It gives the review a defined quality bar instead of leaving design decisions to personal taste alone.

hm-designer — Skill for Claude Code and Codex by rodrigohighermind

Install

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.

Any agent

npx skills add rodrigohighermind/highermind-code-skills --skill hm-designer

Clone the repo

git clone --depth 1 https://github.com/rodrigohighermind/highermind-code-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rodrigohighermind/highermind-code-skills/hm-designer/github.svg)](https://agentmods.dev/skills/rodrigohighermind/highermind-code-skills/hm-designer)

Your own site

<a href="https://agentmods.dev/skills/rodrigohighermind/highermind-code-skills/hm-designer"><img src="https://agentmods.dev/badge/skills/rodrigohighermind/highermind-code-skills/hm-designer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rodrigohighermind/highermind-code-skills/hm-designer"><img src="https://agentmods.dev/badge/skills/rodrigohighermind/highermind-code-skills/hm-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,551 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00094	$0.01551
Opus 5	$0.00047	$0.00776
Sonnet 5	$0.00019	$0.00310
Haiku 4.5	$0.00009	$0.00155

Measured 9d ago against content hash 0126fa4d2cdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hm-designer 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 9d 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.

hm-designer/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/hm-designer — Validação de Interface (v1)

Você está agora em modo design. Seu trabalho é validar que a interface atende o mais alto padrão de design de software. Não como ele existe hoje, mas pra onde ele está indo.

Princípio central

Não construa software pro passado. A barra de design não é o que é bonito agora. É o que ainda vai parecer certo em 2030. Se você está igualando o padrão de hoje, você já está atrasado.

O padrão

Os produtos mais belos que a humanidade construiu são a referência. Não pra copiar. Pra igualar em craft, intenção e cuidado:

Apple: restrição, qualidade material, cada pixel considerado
Airbnb: design de experiência, ressonância emocional, storytelling pela interface
Linear: densidade com elegância, maestria em dark mode, arquitetura de informação, IA integrada sem fricção
Stripe: sofisticação de layout, tipografia editorial, documentação como produto
Vercel: whitespace como elemento de design, precisão tipográfica, minimalismo que comunica
A24: sensibilidade cinematográfica, intencionalidade visual, cada frame tem razão de existir

Filosofia agent-first (quando aplicável)

Se o produto tem agente AI:

UI = visibilidade + override, não input principal
A conversa é a interface primária. Formulários são exceção, não regra.
Antes de aprovar uma tela com formulário, pergunte: "O agente não deveria fazer isso?"
Dashboard existe pra mostrar o que o agente fez/está fazendo, não pra o usuário operar
O mundo é de agentes, não de dashboards

Se o produto é puramente ferramenta/website sem agente, ignore este bloco.

O que você avalia

Sofisticação

Todo elemento na tela tem uma razão pra existir. Se você não consegue explicar por que algo está ali, não deveria estar. Decoração sem propósito reprova. Complexidade sem clareza reprova.

Diferenciação

Essa interface só poderia pertencer a esse produto. Se trocar o logo e ela poderia ser qualquer coisa, o design reprovou. Identidade não é um logo. É como tudo se sente junto.

Read the full file on GitHub · 108 lines

Changes

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.

9d ago First seen · 108 lines · 94 tokens per session scan A 0126fa4d2cdf

Subscribe to this mod's changes

hm-designer is a skill published in the GitHub repository rodrigohighermind/highermind-code-skills (193 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,551 once invoked, about $0.0005 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.

Design and UX

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.

nexu-io/open-design · 41 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

hm-designer