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 skills add kimlawtech/korean-privacy-terms --skill privacy-eugit clone --depth 1 https://github.com/kimlawtech/korean-privacy-termsWrote 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/kimlawtech/korean-privacy-terms/privacy-eu)<a href="https://agentmods.dev/skills/kimlawtech/korean-privacy-terms/privacy-eu"><img src="https://agentmods.dev/badge/skills/kimlawtech/korean-privacy-terms/privacy-eu/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.
<a href="https://agentmods.dev/skills/kimlawtech/korean-privacy-terms/privacy-eu"><img src="https://agentmods.dev/badge/skills/kimlawtech/korean-privacy-terms/privacy-eu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01361 |
| Opus 5.5 | $0.00028 | $0.00544 |
| Sonnet 5.5 | $0.00014 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
privacy-eu 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
privacy-eu — EU GDPR 전용 스킬
호출 즉시 출력 (영문 인터뷰 시작 안내)
Starting EU GDPR Privacy Notice & Terms generator.
인터뷰는 영문·GDPR 용어로 진행합니다. (사용자 답은 한국어로 하셔도 됩니다)
법령: GDPR Art. 13-14, Art. 6, Art. 9, Chapter V, DSA, CRD 14-day withdrawal
몇 가지만 여쭤볼게요.
법령 근거 (MUST READ)
./jurisdictions/eu-gdpr/gdpr-checklist.md— GDPR Art. 13-14 공개 21종·8대 권리·Art. 6 근거·Art. 83 과태료./jurisdictions/eu-gdpr/terms-checklist.md— CRD·DSA·DCD·Unfair Terms./references/glossary.md— 용어 풀이 (DPO·Data Controller·SCCs 등)./references/design-system-detection.md— UI variant
인터뷰 범위
./scripts/interview.md 중 다음만 수행:
유지
- Step 1 서비스 소개 (serviceName·serviceDescription·operatorName·serviceType)
- Step 2 수집 항목 (자동 수집·민감·고유식별)
- Step 6 처리위탁 (→ Art. 28 Processors + 국제 이전 자동 추론)
- Step 9 시행일·개정 여부
- Step 9-EU 전부 (Q9E-1~11)
- Step 10 디자인 스타일
- Step 11 최종 확인
생략 (한국 전용)
- Step 3 수집 방법 (EU는 Art. 14 출처 개념으로 Q9E-6에 통합)
- Step 4 한국식 처리 목적 (Q9E-4 Legal Basis로 대체)
- Step 5 한국식 제3자 제공 (Q9E-8 Recipients로 대체)
- Step 7 한국 CPO (Q9E-2 DPO로 대체)
- Step 8 한국 특수 상황
- 14세 미만 → Q9E-11 (16세 기본)
- AI 자동화·행태광고·전송요구권·국내대리인은 EU는 다르게 처리
사용 템플릿
./jurisdictions/eu-gdpr/privacy-notice.en.mdx.tmpl→src/app/privacy/page.tsx./jurisdictions/eu-gdpr/terms-of-service.en.mdx.tmpl→src/app/terms/page.tsx
치환 프로토콜
./scripts/render.md의 EU GDPR 치환 규칙 섹션 필독. 조건부 블록 13종 해석·검증 키워드 지정됨.
UI 컴포넌트 locale
모든 컴포넌트에 locale="en" prop 박기:
<ConsentModal locale="en" />
<CookieBanner locale="en" variant="center-modal" blocking={true} />
<LabelingCard /* 영문 라벨로 텍스트 대체 */ />
CookieBanner는 GDPR 옵트인 모드:
variant="center-modal"또는variant="bottom-bar"+ 옵트인 UX- Reject all 버튼을 Accept all과 동등 노출 (CNIL·EDPB)
생성 대상 파일 (src-app 기준)
src/mdx-components.tsx
src/content/legal/privacy-policy.mdx (GDPR Privacy Notice)
src/content/legal/terms-of-service.mdx (EU Terms)
src/app/privacy/page.tsx (locale="en")
src/app/terms/page.tsx (locale="en")
src/components/legal/ConsentModal.tsx
src/components/legal/CookieBanner.tsx
src/components/legal/LabelingCard.tsx
What ships with it
4 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.
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.
- 1mo ago First seen · 131 lines · 70 tokens per session scan A 9d40524d7da8
privacy-eu is a skill published in the GitHub repository kimlawtech/korean-privacy-terms (590 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,361 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
korean-law
A legal research connection to South Korea's official law information service. It can retrieve statutes, court decisions, administrative rules, local ordinances, treaties, and legal interpretations, then check cited provisions against the source.
commercial-legal-pl
Skill do analizy i tworzenia umów według polskiego prawa, ze szczególnym uwzględnieniem umów B2B, IP i IT (body leasing, NDA, wdrożenia, SaaS, przeniesienie praw autorskich, ugody). Powstał w Kancelarii Radców Prawnych Żurawska Piotrowski i Wspólnicy (ktzr.pl). Używaj zawsze gdy użytkownik prosi o przeanalizowanie…
recherche-juridique
Méthodologie rigoureuse de recherche en droit français (sources primaires Légifrance, vérification de vigueur, citation traçable). Active ce skill dès que l'utilisateur cite ou demande un article de loi, code, décret, arrêté ou circulaire ; demande une qualification pénale, administrative ou civile ; demande une…
recherche-juridique
Aide à la recherche juridique en droit français.
recherche-juridique
Méthodologie rigoureuse de recherche en droit français (sources primaires Légifrance, vérification de vigueur, citation traçable). Active ce skill dès que l'utilisateur cite ou demande un article de loi, code, décret, arrêté ou circulaire ; demande une qualification pénale, administrative ou civile ; demande une…
recherche-juridique
Méthodologie de recherche et d'analyse du droit français et européen à partir de sources officielles, avec contrôle de provenance, de version, de vigueur, d'applicabilité et de citation. Utiliser pour vérifier ou interpréter un texte, rechercher une jurisprudence, qualifier une situation juridique, rédiger ou auditer…