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-drawing-tagginggit 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-drawing-tagging)<a href="https://agentmods.dev/skills/lsj4232/kr_patent_skill/kr-patent-drawing-tagging"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-drawing-tagging/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-drawing-tagging"><img src="https://agentmods.dev/badge/skills/lsj4232/kr_patent_skill/kr-patent-drawing-tagging.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 | $0.00270 | $0.03001 |
| Opus 5 | $0.00135 | $0.01501 |
| Sonnet 5 | $0.00054 | $0.00600 |
| Haiku 4.5 | $0.00027 | $0.00300 |
Grade A, and why
kr-patent-drawing-tagging 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
한국 특허 도면부호 태깅 (PNG 직접 삽입)
무엇을 하는가
무부호 도면 PNG(블록도·파이프라인도·흐름도)에 도면부호를 이미지 위에 직접 그려 넣어 태깅본 PNG를 만든다. 검증된 파이프라인 (사건 C, 도면 14장 / 부호 98개 실전 검증):
도면 시각 판독 → 부호 체계 확정 → 도면별 anchor 설정(JSON) 작성
→ scripts/tag_drawings.py 실행 (cv2 박스검출 + 최근접 매칭 + 충돌감지 배치)
→ 태깅본 전수 육안 검증 (Read로 이미지 확인) → 어긋난 도면만 설정 수정 후 재실행
→ 부호매핑표 md/xlsx 산출
작업 순서
Step 1. 입력 확보
- 도면 PNG 폴더 (숫자 파일명
1.png,2.png, … 권장) - 확정된 부호 체계 (없으면 kr-patent-symbol-design 먼저 호출)
- 모든 도면을 Read로 시각 판독하여 각 박스의 위치를 파악해 둔다 (anchor 좌표의 근거).
Step 2. 설정 JSON 작성
examples/example_config.json 을 복사하여 사건별로 작성. 도면마다:
| 필드 | 의미 |
|---|---|
solo |
태깅할 단독 박스 [fx, fy, "부호"] — fx/fy는 박스 중심의 이미지 폭·높이 대비 비율(0~1). 시각 판독 시 표시 좌표 ÷ 표시 크기로 추정 |
cyl |
실린더(DB 등) — 내부 하단 중앙에 배치 |
container |
최대 면적 박스(예: 제어부 컨테이너) 부호 — 내부 우상단 |
groups |
점선 그룹: sym(대표 부호), members(멤버 박스 locator 좌표 — 검출 소진용, 무부호), tagged(예외적으로 부호 붙일 멤버 [idx, "부호"]) |
copy_only |
true면 무수정 복사 (부호가 이미 인쇄된 도면) |
anchor는 대략적이어도 된다 — 스크립트가 검출 박스와 최근접 매칭하므로 박스 중심에서 다소 어긋나도 올바르게 붙는다. 박스가 밀집한 도면만 정확히.
Step 3. 실행
두 가지 스타일 엔진 중 선택:
# (a) 인라인 스타일 — 박스 내부 라벨 옆에 숫자
python scripts/tag_drawings.py --config <사건별 config.json>
# (b) KIPO 정식 작도 스타일 — 박스 외부 숫자 + 구불선 지시선 (레퍼런스: 사건 B 작도본)
python scripts/tag_drawings_leader.py --config <사건별 config.json>
leader 엔진(v2) config 확장: figure별 pad_top/left/right/bottom(캔버스 여백 확장 px),
solo 항목 4번째 요소로 배치 방향(above/below/right/right_upper/left/above_left),
groups에 "sides", tagged 항목 3번째 요소로 방향 지정. 1차 실행 리포트의 강제배치(False)
항목을 보고 pad·방향을 넣어 재실행하는 2-pass가 표준. 실전 config:
대학 고객 사건\사건 C_사건수임\도면부호태깅\config_leader.json
- 출력:
out_dir\도NN.png+ 콘솔에 도면별 부호 수·문제 리포트 - 한글 경로의 cv2 imread 실패 → 스크립트가
np.fromfile + imdecode로 처리 (내장됨)
Step 4. 전수 육안 검증 (필수)
태깅본 전부를 Read로 열어 (1) 부호가 올바른 박스에 붙었는지, (2) 라벨 텍스트와 겹치지 않는지 확인. 문제 도면만 anchor 수정 후 재실행. 검증 없이 납품 금지.
Step 5. 매핑표 산출
부호매핑표(md)를 작성하고 xlsx로 변환하여 태깅본과 같은 폴더에 저장: 구분(시스템/데이터/방법 단계) | 부호 | 명칭 | 등장 도면 | 관련 청구항.
배치 엔진 (스크립트 내장 규칙)
What ships with it
3 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.
- 11d ago First seen · 149 lines · 270 tokens per session scan A d8637145cd9d
kr-patent-drawing-tagging is a skill published in the GitHub repository lsj4232/KR_PATENT_SKILL (14 stars, last pushed 18d ago), licensed MIT. It adds 270 tokens to every session and 3,001 once invoked, about $0.0014 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…