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 lsj4232/KR_PATENT_SKILL --skill kr-patent-prior-art-reportgit clone --depth 1 https://github.com/lsj4232/KR_PATENT_SKILLWrote 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/lsj4232/kr_patent_skill/kr-patent-prior-art-report)<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-prior-art-report"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-prior-art-report/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/lsj4232/kr_patent_skill/kr-patent-prior-art-report"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-prior-art-report.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 | $0.00391 | $0.03393 |
| Opus 5 | $0.00196 | $0.01697 |
| Sonnet 5 | $0.00078 | $0.00679 |
| Haiku 4.5 | $0.00039 | $0.00339 |
Grade A, and why
kr-patent-prior-art-report scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL -o "선행특허 N_{cc}{번호}{종별}.pdf" "https://patentimages.storage.googleapis.com/..." How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kr-patent-prior-art-report — 우선심사용 선행기술 조사 패키지 생성
입력 / 산출물
입력: 한국 특허 명세서 .docx (청구항 포함), 케이스 폴더 경로 (docx가 있는 폴더가 기본)
산출물 (모두 케이스 폴더에 저장):
선행특허 1_{cc}{번호}{종별}.pdf~선행특허 4_...pdf— 공보 원문 4건[{REF}]선행기술조사_{발명의 명칭}.md— 조사 보고서[OUR_REF]우선심사신청설명서.hwpx— 특허청 양식 설명서 (파일명 고정: 리터럴 "[OUR_REF]")
워크플로우
1단계: 명세서 파악
python scripts/extract_docx_text.py "<명세서.docx>" <scratchpad>/spec.txt
- Grep으로
【청구항,【발명의 명칭】위치 확인 후 청구항 전체와 과제해결수단을 Read. - 독립항 번호(인용 문구 없는 항: 통상 방법/시스템/프로그램 3건)와 핵심 구성요소를 목록화한다. 핵심 구성요소는 이후 문헌 선정의 커버리지 기준이 된다.
- 특징적 종속항(차별화 포인트가 되는 항)도 2~3개 뽑아둔다.
2단계: 선행특허 4건 검색·검증 (WebSearch + WebFetch)
- WebSearch로
patents.google.com을 대상으로 검색한다. 검색어는 핵심 구성요소별로 국문/영문/중문을 섞어 여러 번 fan-out (예: "볼트 체결 딥러닝 검사 patents.google.com", ""bolt loosening" detection deep learning patent KR"). - 선정 원칙:
- 총 4건. 각 문헌이 서로 다른 핵심 구성요소를 커버하도록 분산 배치 (예: 센서 측정 / AI 판정 / 설계 대비 비교 / 개별 요소기술).
- 국가 혼합 권장 (예: 중국 공개 1건 + 한국 등록/공개 3건). 등록특허 우선.
- 반드시 실존 특허여야 함 — 후보마다
patents.google.com/patent/{번호}/{ko|en}을 WebFetch로 열어 서지사항(명칭·출원인·공개/공고일·청구항 1·법적상태)과 patentimages PDF 링크를 확인한다. 검증 안 되면 교체.
- 각 문헌에 대해 대비 청구항 매핑을 정한다 (독립항 중심, 종속항 보강).
3단계: PDF 다운로드
curl -sL -o "선행특허 N_{cc}{번호}{종별}.pdf" "https://patentimages.storage.googleapis.com/..."
- 파일명 규칙: 한국 등록
kr2292602b1(등록번호 7자리+종별, "10-" 접두 제거), 한국 공개kr20180131471a, 중국cn118654725a. 영문 번역본이면_en접미. - 다운로드 후 각 PDF의 페이지 수를 검증한다 (1~2페이지면 다운로드 실패 의심):
python -c "import re; d=open('파일.pdf','rb').read(); print(len(re.findall(rb'/Type\s*/Page[^s]', d)))"
4단계: 조사 md 작성
파일명: [{REF}]선행기술조사_{발명의 명칭}.md. 구성 (KIPO 우선심사 자체조사 양식 준용):
# [{REF}] 선행기술 조사 — {발명의 명칭}
대상 출원: ... (독립항: 청구항 X(방법), Y(시스템), Z(프로그램))
【검색결과】
1. 중국 공개특허 제XXXXXXXXX호 (YYYY.MM.DD. 공개) ← 공개특허는 "공개", 등록특허는 "공고"
2. 한국 등록특허 제10-XXXXXXX호 (YYYY.MM.DD. 공고)
...
* 문헌 서지 정보: 번호/명칭/출원인/첨부 PDF 파일명
【선행기술과의 대비설명】
| 청구항 | 선행기술 문헌명 | 유사점 | 차이점 | 대비 판단 | ← 문헌별 1행, 총 4행
## 종합 의견 (어느 문헌에도 개시되지 않은 본원 통합 구성 정리)
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.
- 12d ago First seen · 172 lines · 391 tokens per session scan A a6d7440d27d5
kr-patent-prior-art-report is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (15 stars, last pushed 19d ago), licensed MIT. It adds 391 tokens to every session and 3,393 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
eac-habre
Chambres Africaines Extraordinaires (CAE) / Extraordinary African Chambers in the Courts of Senegal (EAC) research, drafting, and analysis — the Hissène Habré case. Use whenever the conversation involves the CAE/EAC, the AU-Senegal Accord of 22 August 2012, the Statute of the Chambers, the Habré trial (2015-2016), the…
jep
Jurisdicción Especial para la Paz (JEP) — Colombia's Special Jurisdiction for Peace — research, drafting, and analysis. Use whenever the conversation involves the JEP, the SIVJRNR / Sistema Integral para la Paz, the 2016 Final Peace Agreement with the FARC-EP, Acto Legislativo 01 de 2017, Ley Estatutaria 1957 de 2019…
nuremberg-tokyo
Post-WWII international military tribunals research, drafting, and analysis: the IMT at Nuremberg (1945-46), the twelve NMT trials under Control Council Law No. 10 (1946-49), and the IMTFE at Tokyo (1946-48). Use whenever the conversation involves Nuremberg, the Tokyo Trial, the London or Tokyo Charters, the IMT or…
reg-64-kosovo
Regulation 64 Panels (Kosovo) research, drafting, and analysis — the UNMIK international judges and prosecutors (IJP) mechanism in the Kosovo district courts, 2000-2008/09. Use whenever the conversation involves UNMIK Regulation 2000/64, the 64 Panels, Regulations 2000/6 and 2001/2, UNSC Resolution 1244 (1999), the…
special-panels-timor-leste
Special Panels for Serious Crimes of the Dili District Court (SPSC, 2000-2006) research, drafting, and analysis. Use whenever the conversation involves the Special Panels, the Serious Crimes Unit (SCU), UNTAET and its Regulations 1999/1, 2000/11, 2000/15 and 2000/30, the 1999 referendum violence, the hybrid…
cps-rca
Cour Pénale Spéciale de la République Centrafricaine (CPS) / Special Criminal Court in the Central African Republic (SCC-CAR) research, drafting, and analysis. Use whenever the conversation involves the CPS, the Loi organique n°15.003 of 3 June 2015, the RPP (Loi 18.010), the affaire Paoua / Lemouna et Koundjili (Issa…