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/kimsanguine/hplan/respectnpx skills add kimsanguine/hplan --skill respectgit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/kimsanguine/hplan/respect)<a href="https://agentmods.dev/skills/kimsanguine/hplan/respect"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/respect.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 | $0.00070 | $0.03332 |
| Opus 5 | $0.00035 | $0.01666 |
| Sonnet 5 | $0.00014 | $0.00666 |
| Haiku 4.5 | $0.00007 | $0.00333 |
Grade A, and why
respect 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
--mode brief:
- 화면 코딩 전에 RESPECT.md 생성 — "respect before design" 원칙
- 5개 핵심 의도 commit: three_second_rule / next_action / social_proof / hierarchy_rules / motion_language
- 결정론 검증 가능한 YAML 스키마 (craft-lint가 픽셀 분석 없이 정합성 검증)
- DESIGN.md (Google 표준 토큰)와 cross-reference 강제
--mode checkpoint:
- 화면 ship 직전 사용자 존중 게이트 mechanical enforcement
- AI 책임: 화면 분류 (screen_type / traffic_level) — Rule 5 허용 영역
- 결정론 책임: 분류 결과 → α/β/γ 게이트 조합 lookup (정책은 사용자 yaml)
- 게이트별 실행은 각각 다른 메커니즘 (인간 / 데이터 / 합성)
Trigger Gate
Use This Skill When
- 새 화면 디자인 시작 (라우팅 추가 직전) →
--mode brief - 기존 화면 리디자인 — RESPECT.md 갱신 →
--mode brief - 사용자 인터페이스가 있는 LLM 에이전트의 PRD Section 11 보강 →
--mode brief - 화면 ship 직전 (deploy / release 이전 마지막 게이트) →
--mode checkpoint - craft-lint 통과 후 (디자인 정합성 확인 후 사용자 존중 게이트) →
--mode checkpoint
Route to Other Skills When
- 표준 토큰 (색·폰트·간격) 정의 → Google DESIGN.md (
npx @google/design.md) - 픽셀 분석 (fold density / contrast) →
deliver/ui-validate --check hierarchy(Playwright) - 디자인 토큰·hierarchy 위반 →
scripts/validate-craft-lint.py(정적) 또는deliver/ui-validate --check hierarchy(런타임) - 게이트 통과의 자연어 보고 →
operate/ops-review
Boundary Checks
- DESIGN.md 부재 시 → "먼저
npx @google/design.md init권유" - 백엔드 only 에이전트 → "RESPECT.md 불필요, PRD Section 11 N/A 표기"
- 매트릭스 yaml 누락 → default 매트릭스 + warning
- β 게이트 + analytics_endpoint 부재 → β 자동 skip + warning
Mode: brief
RESPECT.md 스키마 (필수 5 섹션)
screen: "<화면 이름>"
references_design_md: ./DESIGN.md # 표준 파일 cross-ref 강제
three_second_rule:
what_is_this: "한 문장. 3초 안에 답이 나와야 한다 (≤20 단어, 금지어 없음)"
# 예: "교사가 강의 슬라이드를 5분에 만드는 AI 도구"
# 실패 예: "차세대 AI 기반 교육 콘텐츠 플랫폼" ← 의미 0
scan_test:
if_user_only_reads_headlines: "핵심 가치를 잡을 수 있는가?"
required_headlines: 3
next_action:
primary_cta: "<단 1개 CTA 문구>" # craft-lint: != null + ≤ 6 단어
secondary_cta: null # 처음엔 None. 2개 이상이면 fail
placement: "0.05초 룰 — fold 안"
social_proof:
type: "logo_strip | testimonial | usage_number"
evidence: "<구체 데이터>" # 예: "26M ALTools 사용자"
position: "fold 직후"
emotional_tone:
hero_image_face: "smiling | neutral | candid"
rationale: "<왜 이 표정이 적합한가>"
hierarchy_rules:
max_elements_above_fold: 7
max_type_scale_per_screen: 4
color_ratio: [60, 30, 10] # 합 100 강제 (craft-lint 검증)
whitespace_to_content_min: 0.4
cta_count_above_fold: 1 # 1 강제
motion_language:
hover_transition_ms: 200
page_transition_easing: "cubic-bezier(0.4, 0, 0.2, 1)"
scroll_reveal: "stagger 80ms"
forbidden:
- "차세대, 혁신, 솔루션 같은 추상명사"
- "기능 나열 (이 단계에선 결과만)"
- "fold 안에 4개 이상의 element"
- "Inter / Roboto / Arial / system-ui 폰트 (generic AI aesthetics)"
analytics_endpoint: "<PostHog/Plausible/GA4 URL>" # checkpoint β 게이트
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 · 285 lines · 70 tokens per session scan A ea484a9bdabb
respect is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 20d ago), licensed MIT. It adds 70 tokens to every session and 3,332 once invoked, about $0.0003 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
ui-first-principles
First-principles UI/IA reasoning: turns a + API field set into JTBD analysis, principle-anchored field-priority decisions, anti-pattern findings, and a bidirectional UI↔API gap report. Trigger: UI、UX、資訊架構、IA、scenario-driven UI、欄位優先級、information hierarchy. Not for: visual/CSS work (use /frontend-design), post-build…
creating-figures
Creates publication-quality scientific figures for academic papers. Backend is chosen by host paper extension — .tex papers get TikZ figures, .typ papers get CeTZ figures; the two are never mixed. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses.…
user-testing
Designs user tests in two modes — quick 15-minute concept test on wireframes (3-5 users) or a full usability study (methodology, participants, tasks, severity coding). Use for "concept test", "проверить концепт на пользователях", "usability test", "юзабилити-тест", "user testing", "test the prototype", "план…
design-critique-template
Structured critique of a design against the hypothesis it was drawn for, plus heuristic evaluation — for step 9 and any mockup review. Use for "critique the design", "review mockup", "ревью макета", "что не так с UX", "heuristic evaluation", "оцени дизайн".
ui-pattern-library
Picks UI patterns that address the mechanism of a solution hypothesis — for wireframing in /sketch. Use when sketching a solution, choosing between interface approaches, or when the user says "какой паттерн использовать", "what component to use", "UI pattern", "how should this screen work", "нарисуй экраны".
form-patterns
Справочник паттернов компоновки и UX-правил управляемых форм 1С. Используй как справочник при проектировании форм — архетипы, конвенции, UX-правила элементов, продвинутые приёмы.