Borrowing it
Nothing to install: this file belongs to claude-code-expert/carve-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/claude-code-expert/carve-harness/main/.claude/skills/carve-guide/SKILL.mdgit clone --depth 1 https://github.com/claude-code-expert/carve-harnessWrote 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/claude-code-expert/carve-harness/carve-guide)<a href="https://agentmods.dev/skills/claude-code-expert/carve-harness/carve-guide"><img src="https://agentmods.dev/badge/skills/claude-code-expert/carve-harness/carve-guide.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 | $0.00148 | $0.02867 |
| Opus 5 | $0.00074 | $0.01434 |
| Sonnet 5 | $0.00030 | $0.00573 |
| Haiku 4.5 | $0.00015 | $0.00287 |
Grade C, and why
carve-guide scanned grade C with 2 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find .claude/rules -name '*.md' | wc -l # 규칙 Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills | wc -l # 스킬 (carve-guide 포함 — v0.0.13부터 배포) How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
carve-guide — 하네스 HTML 산출물 작성 스킬
harness의 모든 HTML 산출물을 검증된 디자인 시스템 + 제약으로 만든다. run-ai.kr 게시(임베드)·GitHub Pages 호스팅을 전제로 한다. v0.0.13부터 하네스 번들에 포함 — 소비자도 §0~6(범용 HTML 작성)을 쓴다. §7(릴리스 인벤토리 갱신)만 이 리포 전용이다.
0. 언제 쓰나
- 새 HTML 문서/페이지/리포트/랜딩/데모 작성
- 기존 HTML 디자인·내용 갱신
- 릴리스 시
carve-workflow-guide.html실측 갱신 (§6 특수 모드)
1. 디자인 도구 오케스트레이션 (스킬·플러그인 적극 활용)
HTML 착수 전 아래를 순서대로 검토·발동한다. 방향은 풍부하게 뽑되, 실행은 anti-slop 안에서.
anti-ai-slop(하드 게이트 · 항상 · 필수) — 시각 작업 전 먼저 발동. 금지 목록(그라데이션·글로우·색그림자·blur≥20·장식 모션·이모지 불릿·카드 상단 컬러바·마케팅 상투어)은 예외 없음. 크래프트 상세는.claude/skills/anti-ai-slop/references/visual-craft.md, 리포트 유형이면 같은 폴더의html-report.md를 작성 직전 읽는다. 최종 산출물은 §5의 린터(check-slop.mjs)를 ERROR 0으로 통과해야 한다.theme-factory(색·폰트 방향) — 10개 프리셋(또는 즉석 생성)에서 문서 성격에 맞는 팔레트·폰트 페어링을 능동 선택(기술문서=차분/무채색+청록, 랜딩=대비 강한 단색, 교육=따뜻한 중립 등). 단 anti-slop이 이긴다: 테마의 다색·그라데이션은 버리고 무채색 베이스 + 액센트 1색 + 폰트 페어링만 취한다.frontend-design플러그인 (레이아웃·타이포 방향) — 템플릿 기본값(Inter/system-ui 수렴, 밋밋한 카드 나열)을 피할 의도적 레이아웃·위계·타이포 방향 탐색에 쓴다. anti-slop 금지 목록과 충돌하면 금지 목록이 이긴다.
규칙 순위:
anti-ai-slop(하드) >theme-factory·frontend-design(방향 제안). 디자인 요소는 이 셋을 적극 조합해 풍부하게, 그러나 게이트 위반은 0.
2. 기본 디자인 시스템 (재사용 베이스)
정본 CSS 시작점: docs/html/carve-workflow-guide.html의 <style> 블록을 복사 기반으로 쓴다(검증된 anti-slop 통과본). 핵심 토큰·컴포넌트:
- 폰트: 본문
Pretendard(한/영/숫자 정합), 코드·수치JetBrains Mono. theme-factory가 다른 페어링을 제안하면 그 이유를 CSS 주석 한 줄로 남기고 교체 가능(단 system-ui 기본 수렴 금지). - 색: 무채색 베이스(
--ink/--surface/--border) + 액센트 1색(기본 teal#0F766E, theme-factory 선택색으로 교체 가능). 색은 의미(위계·상태·판정)에만. - 구획:
1px solid border+ 여백. 그림자는 중성 회색 1단계 또는 없음. - 컴포넌트:
.callout(accent/warn/good),.mono-panel(고정폭 요약),table(1px border),.doc-meta(3열 메타),nav.toc(2열 목차). 필요한 것만 가져오고 안 쓰는 규칙은 제거(죽은 CSS 금지). - CSS는 인라인(
<style>) — 임베드 CSPstyle-src 'unsafe-inline'만 허용, 외부 CSS 링크는 차단될 수 있다.
3. 레이아웃 폭 + 임베드 안전 (필수 · 검증됨)
3.1 폭 — 기본 1000px, !important 고정
run-ai.kr는 이 HTML을 <iframe srcdoc="…">로 감싸고 <head> 최상단에 .wrap{max-width:80%!important;margin-left:0!important}를 주입한다. 파일 .wrap은 소스 순서상 뒤라 !important로 그 주입을 이긴다(같은 specificity는 뒤 규칙 승 — 실측: computed max-width=1000px). 따라서:
.wrap { max-width: 1000px !important; margin: 0 auto !important; padding: 64px 32px 96px; }
@media print { .wrap { padding: 0; max-width: none !important; } }
@media (max-width: 640px) { .wrap { padding: 32px 18px 64px; } } /* 좁으면 자연 축소(반응형) */
What ships with it
1 file 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.
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.
- today Changed · +5 lines d8462c219614
- 8d ago First seen · 124 lines · 148 tokens per session scan C 78b240df8193
carve-guide is a skill published in the GitHub repository claude-code-expert/carve-harness (13 stars, last pushed 2d ago), licensed MIT. It adds 148 tokens to every session and 2,867 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
better-colors
Helps you build a color system and answer anything about color in your project. You can generate palettes, use semantic tokens, convert between formats, check contrast and more.