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-search-querygit 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-search-query)<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-search-query"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-search-query/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-search-query"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-search-query.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 | $0.00377 | $0.02334 |
| Opus 5 | $0.00188 | $0.01167 |
| Sonnet 5 | $0.00075 | $0.00467 |
| Haiku 4.5 | $0.00038 | $0.00233 |
Grade A, and why
kr-patent-search-query 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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kr-patent-search-query
기술분류 소분류별 특허 검색식을 국문/영문 2단 → 통합본 → IPC 결합본 정형으로 생성한다. 산출물은 keywert/KIPRIS에 바로 붙여 건수 비교가 가능한 연산검색식이다.
입력
- (필수) 소분류명 1개 이상. 보통 기술분류표의 (중분류 → 소분류) 구조로 받는다.
- (택1) 각 소분류의 핵심 키워드 목록 또는 원자료(사업계획서·논문·IDS). 원자료만 있으면 먼저 소분류별 키워드를 추출한 뒤 검색식으로 변환한다.
- (옵션) 형제 소분류 목록 — 상호배타 처리(아래 D원칙)를 위해 함께 받는 것을 권장.
출력 정형 (소분류 1개당 4블록)
블록 1 — 기본 키워드 (국문)
((디바이스·구조군 동의어 OR ...))
AND
((특성·동작군 동의어 OR ...))
블록 2 — 확장 키워드 (영문)
((device/structure synonyms OR ...))
AND
((characteristic/action synonyms OR ...))
블록 3 — 통합본 = (국문 전체) OR (영문 전체) ★기본 최종 산출물
(
(블록1 국문식 전체)
)
OR
(
(블록2 영문식 전체)
)
블록 4 — IPC 결합본 (노이즈 컷, 권장)
[블록3 통합식] AND (IPC = 핵심분류* OR 보조분류*)
구조 원칙 (A~F) — 반드시 적용
A. 2군 AND 구조. 모든 식은 (디바이스·구조군) AND (특성·동작군).
- 디바이스·구조군 = 그 소분류가 다루는 물건/대상(소자·렌즈·경통·모듈 등)의 동의어 OR 묶음.
- 특성·동작군 = 그 물건에 대한 기능·특성·공정·평가(고출력·정렬·방열·결합효율 등)의 동의어 OR 묶음.
- 두 군 사이만 AND, 군 내부는 전부 OR.
B. 연산자 정형.
*= 절단(어간). 예:안정*(안정/안정성/안정화),stabil*.A/n= 인접·순서 유지, n어절 내. 예:(레이저 A/1 다이오드),(beam A/1 profile).N/n= 근접·순서 무관, n어절 내. 예:(high N/1 (power OR output))."..."= 구문(붙은 표현) 검색. 예:"laser diode*","405nm". 엔진이 구문검색을 안 받으면(laser A/1 diode*)형태로 자동 대체.- 약어/숫자단위는 띄어쓰기 변형까지:
"405nm" OR (405 A/1 nm).
C. 동의어 3축 확보. 각 OR 묶음은 가능하면 ① 정식용어 ② 구어/약어 ③ 영문음차/표기변형을 포함. (국문 블록에도 흔히 영문으로 쓰이는 약어 LD·UV·FWHM·M2 등은 넣는다.)
D. 형제 소분류 상호배타(중첩 금지). 같은 중분류 안 다른 소분류의 핵심어를 일부러 배제한다.
- 예: 레이저다이오드(소자) 소분류 식에는 집광/렌즈/콜리메이터 계열을 넣지 않는다.
- 같은 단어가 목적에 따라 두 소분류에 걸치면(예 "본딩"=고정용 vs 정렬확정용) 더 좁은 맥락어와 A/n로 묶어 귀속을 분리하고, 그 판단 근거를 노트로 남긴다.
E. 통합은 블록-OR가 기본. (국문 전체) OR (영문 전체)를 기본으로 한다.
- 대안인
(국문소자 OR 영문소자) AND (국문특성 OR 영문특성)은 언어 교차 매칭(국문소자+영문특성) 까지 잡혀 노이즈가 커진다. 명세서/초록은 보통 단일 언어이므로 교차 매칭 이득이 작다. - 사용자가 "교차 통합/한 군씩 합쳐"라고 명시할 때만 대안식을 쓴다.
F. 검색량 조절 가이드 동봉. 각 소분류 식 끝에 2줄을 붙인다.
- 과다 시: 특성군에서
설계*·coheren*같은 광범위 단어를 제거하고 핵심특성 2~3개로 축소. - 과소 시: 수치/파장 제약을 풀고 소재·상위개념 키워드(예
(GaN OR 질화갈륨 OR InGaN))를 OR 추가.
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.
- 11d ago First seen · 121 lines · 377 tokens per session scan A fb494c3b4026
kr-patent-search-query is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 377 tokens to every session and 2,334 once invoked, about $0.0019 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 2026-08-30.
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…
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…
eccc
Extraordinary Chambers in the Courts of Cambodia (ECCC, Khmer Rouge Tribunal) research, drafting, and analysis. Use whenever the conversation involves the ECCC, Case 001 (Duch), Case 002 (NUON Chea, KHIEU Samphan) including the severance into Cases 002/01 and 002/02, Cases 003 and 004, the ECCC Law, the Internal…