kordoc is a command-line tool and MCP server that reads Korean document formats and converts, compares, analyzes, fills, or generates them, including HWP, PDF, Office files, and images. Government workers and other users handling Korean documents use it to make their contents available as Markdown and automate document processing, while the catalogue entries provide integrations and workflows for coding agents.
Borrowing it
Nothing to install: this file belongs to chrisryugj/kordoc. 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/chrisryugj/kordoc/main/.claude/skills/gongmunseo/SKILL.mdgit clone --depth 1 https://github.com/chrisryugj/kordocWrote 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/chrisryugj/kordoc/gongmunseo)<a href="https://agentmods.dev/skills/chrisryugj/kordoc/gongmunseo"><img src="https://agentmods.dev/badge/skills/chrisryugj/kordoc/gongmunseo/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/chrisryugj/kordoc/gongmunseo"><img src="https://agentmods.dev/badge/skills/chrisryugj/kordoc/gongmunseo.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00286 | $0.02767 |
| Opus 5 | $0.00143 | $0.01384 |
| Sonnet 5 | $0.00057 | $0.00553 |
| Haiku 4.5 | $0.00029 | $0.00277 |
Grade A, and why
gongmunseo 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
공문서(公文書) 생성 스킬
내용·주제를 받아 한국 행정 공문서 표준 서식의 HWPX로 생성한다.
서식 표준은 행정안전부 「행정업무운영편람」·「행정업무의 운영 및 혁신에 관한 규정」 시행규칙 근거.
실제 렌더링(항목부호 행갈굼·여백·폰트)은 kordoc 공문서 모드(kordoc generate --preset)가 담당하므로,
이 스킬은 (1) 종류 판별 → (2) 내용을 표준 구조의 마크다운으로 작성 → (3) 변환 → (4) 경로 안내 만 한다.
절차
1. 문서 종류 판별 → 프리셋
| 사용자 의도 | 프리셋 | 항목부호 | 비고 |
|---|---|---|---|
| 대외 공문/시행문 | 기안문 |
8단계 1. 가. 1) |
두문·본문·결문 |
| 정책·검토·결과 보고 | 보고서 |
불릿 □ ○ - ㆍ + 헤딩 |
개조식, 1건1매 |
| 사업·행사 계획 | 계획서 |
8단계 | 5W2H 골격 |
| 알림·통지·안내 | 통지 |
8단계 | 경어 종결 |
| 회의 기록 | 회의록 |
8단계 | 법정 9요소 |
의도가 모호하면 AskUserQuestion으로 종류를 확인한다. (예: "보고서로 할까요, 대외 시행문(기안문)으로 할까요?")
2. 템플릿 로드 + 내용 채우기
해당 templates/<종류>.md를 Read로 읽어 골격을 파악하고, 사용자 내용으로 채운다.
- 부족한 필수 정보(기관명, 수신처, 담당자·연락처, 시행일 등)는 사용자에게 묻거나, 모르면
○○○/[기관명]같은 플레이스홀더로 두고 "채워야 할 항목"을 마지막에 안내한다. 임의로 지어내지 말 것. - 본문은 아래 표기법과 항목부호 규칙을 반드시 지켜 작성한다.
3. 마크다운 작성 규칙 (kordoc 공문서 모드가 인식하는 형식)
항목부호 = 중첩 리스트의 깊이로 표현. 마커 종류(-/1.)는 무시되고 깊이 → 부호가 강제된다.
들여쓰기 2칸 = 한 단계.
1. 첫째 항목 내용 ← 깊이0 → "1."
- 둘째 항목 ← 깊이1(2칸) → "가."
- 셋째 항목 ← 깊이2(4칸) → "1)"
- 넷째 항목 ← 깊이3(6칸) → "가)"
2. 다음 첫째 항목 → "2."
- 깊이별 부호: 0=
1.1=가.2=1)3=가)4=(1)5=(가)6=①7=㉮(자동 생성·자동 정렬) - 항목이 하나뿐이면 리스트로 만들지 말고 본문 단락으로 바로 쓴다(규정: 단일 항목은 부호 생략 — 엔진도 자동 생략하지만 구조를 단순히).
- 보고서(
--preset 보고서)는 리스트 깊이가□ ○ - ㆍ불릿으로 나오고, 대제목/중제목은#/##헤딩으로 쓴다. - 가운데 정렬(행정기관명·발신명의)은
<center>광 진 구 청</center>한 줄로. - 제목/기관명은
#(h1) — 공문서 모드에서 가운데·크게 렌더된다.
4. 표기법 (본문 작성 시 직접 지킬 것 — 엔진이 안 고쳐줌)
| 항목 | 규칙 | 예 |
|---|---|---|
| 날짜 | YYYY. M. D. 온점+1칸, 월·일 0 제거, 끝에도 온점 |
2026. 6. 19. / 2026. 6. 19.(금) |
| 기간 | 물결표 ∼ |
6. 1.∼6. 15. |
| 시각 | 24시각제 HH:MM, 시·분 0 표기 |
09:00, 14:30 |
| 금액 | 숫자+한글 병기, 붙여씀 | 금113,560원(금일십일만삼천오백육십원) |
| 붙임 | 붙임 뒤 2칸(쌍점 X), 1개면 번호 생략 |
붙임 ○○○ 1부. 끝. |
| 끝 | 본문/붙임 마지막에 2칸 띄우고 | …바랍니다. 끝. |
| 법령명 | 낫표 | 「행정업무의 운영 및 혁신에 관한 규정」 |
| 쌍점 | 앞 붙이고 뒤 1칸(본문·항목). 표 셀의 라벨 "성 명 :"은 법정 서식 관행이라 lint 대상 아님(v4.12.3) | 일시: 2026. 6. 19. |
| 어투 | 시행문·통지=경어("~하시기 바랍니다") / 보고서·계획서=개조식 명사형("~함/~임") |
What ships with it
8 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.
- 5d ago Changed · +13 lines be33e878c372
- 12d ago First seen · 100 lines · 286 tokens per session scan A 4b5dca044e3c
gongmunseo is a skill published in the GitHub repository chrisryugj/kordoc (1,817 stars, last pushed yesterday), licensed MIT. It adds 286 tokens to every session and 2,767 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
ai-hwp-reader
A read-only tool for opening Korean HWP and HWPX word-processing files, or ZIP archives containing them, without Hancom Office. It converts the contents to Markdown while preserving document structure.
ai-hwp-reader
An AI skill that tells a coding agent how to read Korean HWP and HWPX word-processing files, including files inside ZIP archives. It extracts the content and then uses it to complete the user's requested task.
all2md
Convert, read, generate, search, and compare documents with the all2md CLI and Python library. Use whenever a task involves reading or extracting text/tables from a document (PDF, Word, PowerPoint, Excel, HTML, email, EPUB, Jupyter, images, or 100+ source-code and text file types); converting between formats…
form-fill
Use this workflow when filling an existing HWPX across native fields, labeled cells, canonical paths, and body anchors through one analyzed, atomic, and verified mixed-form transaction.
reference-preserving-edit
Use this workflow when editing an existing HWPX while minimizing layout drift by copying first, inspecting the relevant package parts, making bounded edits with the current MCP tools, and validating the result before handoff.
template-generation
Use this workflow when generating an HWPX from an approved template or from a new blank document by orchestrating the current MCP text, table, style, and copy tools without adding new public server tools.