uiux-auditor

uiux-auditor is a skill for Codex from HYEXE/codex-plugins. It costs 198 tokens per session (1,535 once invoked), scanned A, original, Apache-2.0.

A method for reviewing a user interface—the screens and interactions people use in a product—using screenshots, websites, prototypes, code, or described user flows. It checks observable problems and separates confirmed facts from assumptions and untested behaviour.

In plain words
What is it for?
It is for auditing screens and multi-step tasks, reviewing prototypes or live products, checking accessibility and interface states, and planning how fixes will be verified.
Why use it?
It helps find usability, accessibility, content, responsive-layout, performance, and safety problems before release. It also ranks issues by severity, user impact, evidence, and repair priority.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python3 ../uiux-advisor/scripts/search_kb.py --query "<대상, 과업, 관찰 문제>" --top 8 --json.

Good fit It is for auditing screens and multi-step tasks, reviewing prototypes or live products, checking accessibility and interface states, and planning how fixes will be verified.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HYEXE/codex-plugins
agentmods
npx agentmods add skills/hyexe/codex-plugins/uiux-auditor

Made for: 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.

agentmods badge for uiux-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/hyexe/codex-plugins/uiux-auditor/github.svg)](https://agentmods.dev/skills/hyexe/codex-plugins/uiux-auditor)
Your own site
<a href="https://agentmods.dev/skills/hyexe/codex-plugins/uiux-auditor"><img src="https://agentmods.dev/badge/skills/hyexe/codex-plugins/uiux-auditor/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.

agentmods 80×15 button for uiux-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/hyexe/codex-plugins/uiux-auditor"><img src="https://agentmods.dev/badge/skills/hyexe/codex-plugins/uiux-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,535 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00198 $0.01535
Opus 5.5 $0.00079 $0.00614
Sonnet 5.5 $0.00040 $0.00307
Haiku 4.5 $0.00020 $0.00153

Measured 2mo ago against content hash 739ea4725543, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uiux-auditor 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 2mo 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.

plugins/uiux-advisor/skills/uiux-auditor/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI/UX Auditor

화면과 사용자 흐름에서 관찰 가능한 문제를 근거로 식별하고 수정 우선순위를 정한다. 취향 평가보다 사용자 과업, 접근성, 상태 완전성, 위해 가능성과 검증 가능성을 우선한다.

시작 절차

  1. 대상 제품, 사용자, 플랫폼, 핵심 과업과 감사 범위를 확인한다.
  2. 입력 증거를 정적 화면, 실행 가능한 URL, 프로토타입, 코드, 흐름 설명으로 분류한다.
  3. 확인 가능한 사실, 맥락적 추론과 미검증 동작을 분리한다.
  4. 이 스킬 디렉터리를 기준으로 references/audit-rubric.md를 읽는다.
  5. 기존 지식베이스를 검색하고 직접 관련된 2~5개 가이드만 읽는다.
python3 ../uiux-advisor/scripts/search_kb.py --query "<대상, 과업, 관찰 문제>" --top 8 --json

필요하면 category, source 또는 guide ID로 좁힌다.

python3 ../uiux-advisor/scripts/search_kb.py --list-categories
python3 ../uiux-advisor/scripts/search_kb.py --category "<category>" --query "<query>" --top 8 --json
python3 ../uiux-advisor/scripts/search_kb.py --id <guide-id> --full

증거별 확인 범위

정적 화면·스크린샷

레이아웃, 시각적 위계, 표시된 콘텐츠, 가시 상태와 명시적 단서만 관찰 사실로 다룬다. 키보드, 포커스 순서, 동적 알림, 로딩 전이, 오류 복구, 확대·reflow와 보조기술 동작은 미검증으로 표시한다.

실행 가능한 URL·프로토타입

사용 가능한 브라우저 기능으로 핵심 과업을 직접 수행한다. 정상 경로만 보지 말고 로딩, 빈 상태, 오류, 취소, 뒤로 가기, 반복 실행과 작은 화면을 범위에 맞게 확인한다. 확인하지 않은 환경과 보조기술 지원을 추정하지 않는다.

코드

렌더링 결과와 구현을 구분한다. semantic structure, 이름·역할·상태, focus management, 오류 연결, responsive behavior와 reduced motion 처리를 확인하되 실제 브라우저 검증 없이 동작을 단정하지 않는다.

다단계 흐름

진입 조건, 핵심 단계, 완료 상태, 실패·이탈·복구 경로와 irreversible action을 연결해 본다. 한 화면의 문제와 전체 흐름의 문제를 구분한다.

감사 절차

1. 과업과 성공 상태 고정

사용자가 무엇을 이해하고 결정하고 완료해야 하는지 먼저 적는다. 제품 목표만 있고 사용자 결과가 불명확하면 이를 첫 번째 위험으로 기록한다.

2. 증거 목록 작성

확인한 화면, 상태, 인터랙션, 코드와 환경을 짧게 기록한다. 보지 못한 상태를 존재하지 않는다고 판단하지 않는다.

3. 상태와 경로 점검

범위에 맞게 다음을 확인한다.

  • 정상·로딩·빈 상태·성공·오류·취소·복구
  • 입력, validation, destructive action과 undo
  • 권한, 동의, 개인정보와 민감한 결정
  • 반응형, 확대, 터치, 키보드, 포커스와 motion reduction
  • 콘텐츠 이해, 현실적 극단값과 localization
  • perceived performance와 중복 실행 방지

4. 근거 검색

관찰 문제를 일반 키워드만으로 검색하지 않는다. 대상, 사용자 과업, 상태와 예상 영향을 함께 넣는다. 검색 결과는 순위만 믿지 말고 개별 가이드의 적용 조건과 출처를 읽는다.

5. 이슈 판정

각 이슈에 심각도와 근거 확실도를 별도로 부여한다. 같은 근본 원인의 증상을 여러 이슈로 부풀리지 않는다. 문제 없는 영역을 억지로 채우지 않는다.

6. 수정과 검증 연결

수정안은 디자인 방향만 제시하지 말고 예상 사용자 결과와 검증 방법을 포함한다. 수치 기준은 출처나 제품 요구가 있을 때만 사용한다.

Read the full file on GitHub · 120 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2mo ago First seen · 120 lines · 198 tokens per session scan A 739ea4725543

Subscribe to this mod's changes

uiux-auditor is a skill published in the GitHub repository HYEXE/codex-plugins (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 198 tokens to every session and 1,535 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

design

Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…

OutlineDriven/odin-codex-plugin · 151 tokens

unity-ui-art-and-motion-production

Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…

hoatv2211/GameStudio-CodexKIT · 83 tokens

windows-appshot

Use when the user invokes $windows-appshot or asks to create a Windows appshot bundle, including foreground-window screenshots, UI Automation text, metadata.json, prompt.md, or appshots generated by scripts/New-Appshot.ps1.

josephbartlett/windows-appshot-codex · 50 tokens

edgespark-frontend-design

Design and redesign EdgeSpark frontends with distinctive, production-grade visual direction instead of generic AI-looking UI. Use when building or polishing landing pages, marketing sites, dashboards, auth flows, portfolios, product surfaces, or reusable frontend sections in EdgeSpark, especially when the task…

edgesparkhq/codex-plugins · 87 tokens

stss

Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve…

lennney/stop-that-shit · 75 tokens

methodology-curator

Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.

athola/claude-night-market · 21 tokens