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/hyexe/codex-plugins/uiux-advisornpx skills add HYEXE/codex-plugins --skill uiux-advisorgit clone --depth 1 https://github.com/HYEXE/codex-pluginsWhat 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 | $0.00196 | $0.01310 |
| Opus 5 | $0.00098 | $0.00655 |
| Sonnet 5 | $0.00039 | $0.00262 |
| Haiku 4.5 | $0.00020 | $0.00131 |
Grade A, and why
uiux-advisor 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI/UX Advisor
공개 표준, 공공 서비스 지침, 공개 디자인 시스템, UX 연구 자료를 종합한 한국어 지식베이스를 사용한다. 추측보다 근거 추적, 상태 완전성, 접근성, 사용자 위해, 검증 가능성을 우선한다.
시작 절차
-
사용자의 요청에서 대상 제품·화면·사용자·플랫폼·과업·제약·원하는 산출물을 추출한다.
-
요청을
설명,비교,설계안 검토,명세,계획중 하나 또는 복수 모드로 분류한다. -
이 스킬 디렉터리를 기준으로 검색기를 실행한다.
python3 scripts/search_kb.py --query "<질문과 핵심 맥락>" --top 8 --json -
상위 결과에서 직접 관련된 2~5개 문서만 읽는다. 필요할 때 관련 가이드와 출처 레지스트리로 확장한다.
-
프론트엔드 도구를 비교해야 하면 구조화 레지스트리를 검색한다.
python3 scripts/search_toolkits.py --role "<role>" --ecosystem "<ecosystem>" --recommend --max-risk "<risk>" --top 5 -
time_sensitive: true이거나 도구 도입을 결정하면 현재 공식 자료를 확인하고, 확인할 수 없는 항목을 미검증으로 표시한다. 추천 순서는 리스크·생태계 직접 지원·도입 방식을 설명하는 후보 정렬이지 보편적 품질 점수가 아니다. 현재 설치 여부·기능 적합성·검증 비용은 실제 저장소에서 따로 판단한다. -
답변에서
표준 요구,출처 기반 종합,실무 권고,맥락적 추론을 구분한다.
산출 모드
설명
정의 → 적용 상황 → 핵심 원리 → 예외 → 사례 → 검증 질문 순서로 작성한다.
비교
먼저 비교 차원을 정한다. 각 대안의 적합 조건, 장점, 비용, 실패 위험, 선택 규칙을 같은 차원에서 비교한다.
설계안 검토
화면·URL·프로토타입·코드·실행된 흐름처럼 관찰 가능한 증거가 있으면 uiux-auditor를 사용한다. 이 모드는 증거가 없는 아이디어·문서·명세 초안만 검토한다.
다음 필드를 사용한다.
[위험] 검토 항목
적용 기준:
예상 사용자 영향:
수정안:
검증 방법:
근거 가이드:
제공된 아이디어·문서에 없는 동작과 사용자 결과를 사실처럼 만들지 않고 가정 또는 검증 항목으로 표시한다.
명세
최소한 다음을 포함한다.
- 사용자·과업·성공 상태
- 상태, 이벤트, 전이, 우선순위
- 콘텐츠와 현실적 극단값
- 데이터·권한·개인정보
- 로딩·빈 상태·성공·오류·취소·복구
- 반응형·확대·RTL
- 키보드·포커스·이름·역할·상태
- 터치·포인터·모션 감소
- 성능·분석·인수 기준
계획
결정 질문 → 가정 → 방법 → 대상·모집 → 과업·자극물 → 윤리·개인정보 → 분석 → 성공·반증 기준 → 다음 결정으로 작성한다.
근거 규칙
- 규범 표준을 실무 권고와 같은 수준으로 섞지 않는다.
- 특정 공개 디자인 시스템의 패턴은 비교 사례이며 보편 규칙이 아니다.
- 수치, 사용자 행동, 기술 지원, 규정 준수를 근거 없이 만들지 않는다.
- 자동 검사만으로 접근성 준수를 판정하지 않는다.
- 추천마다 사용자 영향, 트레이드오프, 검증 방법을 연결한다.
지식베이스 위치
- 인덱스:
references/kb/INDEX.md - 에이전트 사용 지침:
references/kb/AGENT_USAGE.md - 출처 레지스트리:
references/kb/SOURCE_REGISTRY.md - 구조화 데이터:
references/kb/guides.jsonl - 개별 가이드:
references/kb/guides/ - 프론트엔드 도구 레지스트리:
references/frontend-toolkit-registry.json
답변 마감 검사
- 해결책 전에 사용자 문제와 결과를 명시했는가?
- 정상 경로 외 상태와 복구를 다뤘는가?
- 접근성·콘텐츠·성능·윤리 위험을 필요한 수준으로 포함했는가?
- 관찰된 사실과 추론·가정을 구분했는가?
- 실행 가능한 검증 방법과 근거 가이드를 표시했는가?
What ships with it
60 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.
- agents/openai.yaml 344 B
- assets/icon.svg 667 B
- references/frontend-toolkit-registry.json 30 KB
- references/kb/AGENT_USAGE.md 3.7 KB
- references/kb/ALL_GUIDES.md 536 KB
- references/kb/GLOSSARY.md 5.6 KB
- references/kb/guides.jsonl 282 KB
- references/kb/guides/01_strategy_ethics/001-outcome-based-design-decisions.md 11 KB
- references/kb/guides/01_strategy_ethics/002-human-centered-problem-framing.md 11 KB
- references/kb/guides/01_strategy_ethics/003-ux-strategy-and-evidence-portfolio.md 11 KB
- references/kb/guides/01_strategy_ethics/004-ethical-and-nondeceptive-design.md 11 KB
- references/kb/guides/01_strategy_ethics/005-human-ai-experience-design.md 12 KB
- references/kb/guides/02_research_discovery/006-research-questions-and-method-selection.md 11 KB
- references/kb/guides/02_research_discovery/007-interviews-and-contextual-inquiry.md 10 KB
- references/kb/guides/02_research_discovery/008-surveys-and-quantitative-research.md 10 KB
- references/kb/guides/02_research_discovery/009-task-journey-and-research-synthesis.md 10 KB
- references/kb/guides/02_research_discovery/010-inclusive-recruitment-and-accessibility-research.md 11 KB
- references/kb/guides/02_research_discovery/011-research-repository-and-decision-log.md 11 KB
- references/kb/guides/03_information_content/012-information-architecture-and-navigation-model.md 11 KB
- references/kb/guides/03_information_content/013-search-filter-and-sort.md 12 KB
- references/kb/guides/03_information_content/014-content-design-and-plain-language.md 11 KB
- references/kb/guides/03_information_content/015-labels-microcopy-and-instructions.md 11 KB
- references/kb/guides/03_information_content/016-localization-and-internationalization.md 11 KB
- references/kb/guides/04_interaction_flows/017-user-flows-and-task-completion.md 11 KB
- references/kb/guides/04_interaction_flows/018-forms-and-validation.md 12 KB
- references/kb/guides/04_interaction_flows/019-feedback-system-status-loading-and-progress.md 12 KB
- references/kb/guides/04_interaction_flows/020-errors-recovery-and-undo.md 11 KB
- references/kb/guides/04_interaction_flows/021-empty-first-use-and-onboarding-states.md 11 KB
- references/kb/guides/04_interaction_flows/022-permissions-consent-and-privacy-choices.md 11 KB
- references/kb/guides/04_interaction_flows/023-destructive-and-high-risk-actions.md 11 KB
- references/kb/guides/05_components_patterns/024-buttons-and-action-hierarchy.md 11 KB
- references/kb/guides/05_components_patterns/025-navigation-patterns.md 11 KB
- references/kb/guides/05_components_patterns/026-dialogs-drawers-and-overlays.md 11 KB
- references/kb/guides/05_components_patterns/027-tables-lists-and-data-dense-interfaces.md 11 KB
- references/kb/guides/05_components_patterns/028-selection-controls-and-input-components.md 11 KB
- references/kb/guides/05_components_patterns/029-notifications-messages-and-alerts.md 11 KB
- references/kb/guides/06_visual_responsive/030-visual-hierarchy-and-layout.md 11 KB
- references/kb/guides/06_visual_responsive/031-typography-and-readability.md 11 KB
- references/kb/guides/06_visual_responsive/032-color-contrast-and-noncolor-cues.md 11 KB
- references/kb/guides/06_visual_responsive/033-responsive-adaptive-and-reflow-design.md 11 KB
- references/kb/guides/06_visual_responsive/034-motion-animation-and-reduced-motion.md 12 KB
- references/kb/guides/07_accessibility_inclusion/035-semantic-structure-and-keyboard-operation.md 11 KB
- references/kb/guides/07_accessibility_inclusion/036-focus-visibility-and-management.md 11 KB
- references/kb/guides/07_accessibility_inclusion/037-accessible-names-roles-states-and-aria.md 11 KB
- references/kb/guides/07_accessibility_inclusion/038-touch-targets-pointer-alternatives-and-zoom.md 11 KB
- references/kb/guides/07_accessibility_inclusion/039-cognitive-accessibility-and-reduced-complexity.md 11 KB
- references/kb/guides/08_validation_metrics/040-prototype-fidelity-selection.md 12 KB
- references/kb/guides/08_validation_metrics/041-usability-testing.md 12 KB
- references/kb/guides/08_validation_metrics/042-heuristic-and-standards-review.md 12 KB
- references/kb/guides/08_validation_metrics/043-product-ux-and-task-metrics.md 12 KB
- references/kb/guides/08_validation_metrics/044-experimentation-and-evidence-quality.md 12 KB
- references/kb/guides/09_systems_delivery/045-design-system-governance.md 12 KB
- references/kb/guides/09_systems_delivery/046-tokens-components-variants-states.md 12 KB
- references/kb/guides/09_systems_delivery/047-content-and-accessibility-component-contracts.md 13 KB
- references/kb/guides/09_systems_delivery/048-handoff-and-acceptance-criteria.md 12 KB
- references/kb/guides/09_systems_delivery/049-design-qa-and-regression-validation.md 12 KB
- references/kb/guides/09_systems_delivery/050-performance-and-perceived-performance.md 12 KB
- references/kb/INDEX.md 16 KB
- references/kb/SOURCE_REGISTRY.md 12 KB
- references/kb/sources.json 20 KB
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 · 100 lines · 196 tokens per session scan A 16bef2520535
uiux-advisor is a skill published in the GitHub repository HYEXE/codex-plugins (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 196 tokens to every session and 1,310 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
stop-that-shit
Keep coding agents focused on requested and necessary work. Use for bounded changes, review-only tasks, scope creep, speculative hardening, unnecessary hashing or dependencies, repeated audit loops, or when the user invokes Stop That Shit.
dev-flow
Use Dev Flow for bounded Codex software development tasks: implementation, bug fixes, refactoring, targeted testing, development delivery, and explicit parallel batches isolated in separate Git worktrees. It may be selected implicitly for those tasks or explicitly with $dev-flow-codex:dev-flow. Do not create a Dev…
codexkit-repository-maintenance
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
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…
decision-report
Generate a portable stakeholder decision report for a CV deployment decision. TRIGGER when: user explicitly asks for a decision report, manager report, or stakeholder doc after a cost crossover has been computed; phrases: "write me a decision report", "generate a report for my manager", "I need a stakeholder doc"…