Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-sharenpx agentmods add skills/joonlab/joonlab-claudecode-setting-for-share/hwpxWrote 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/joonlab/joonlab-claudecode-setting-for-share/hwpx)<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/hwpx"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/hwpx.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.06612 |
| Opus 5 | $0.00021 | $0.03306 |
| Sonnet 5 | $0.00008 | $0.01322 |
| Haiku 4.5 | $0.00004 | $0.00661 |
Grade A, and why
hwpx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HWPX 문서 스킬 — XML-first 워크플로우
한글(Hancom Office)의 HWPX 파일을 XML 직접 작성 중심으로 생성, 편집, 읽기할 수 있는 스킬. HWPX는 ZIP 기반 XML 컨테이너(OWPML 표준)이다. python-hwpx API의 서식 버그를 완전히 우회하며, 세밀한 서식 제어가 가능하다.
환경
# SKILL_DIR는 이 SKILL.md가 위치한 디렉토리의 절대 경로로 설정
SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)" # 스크립트 내에서
# 또는 Claude Code가 자동으로 주입하는 base directory 경로를 사용
# Python 가상환경 (프로젝트에 맞게 설정)
VENV="<프로젝트>/.venv/bin/activate"
모든 Python 실행 시:
# 프로젝트의 .venv를 활성화 (pip install lxml 필요)
source "$VENV"
디렉토리 구조
.claude/skills/hwpx/
├── SKILL.md # 이 파일
├── scripts/
│ ├── office/
│ │ ├── unpack.py # HWPX → 디렉토리 (XML pretty-print)
│ │ └── pack.py # 디렉토리 → HWPX
│ ├── build_hwpx.py # 템플릿 + XML → .hwpx 조립 (핵심)
│ ├── analyze_template.py # HWPX 심층 분석 (레퍼런스 기반 생성용)
│ ├── validate.py # HWPX 구조 검증
│ └── text_extract.py # 텍스트 추출
├── templates/
│ ├── base/ # 베이스 템플릿 (Skeleton 기반)
│ │ ├── mimetype, META-INF/*, version.xml, settings.xml, Preview/*
│ │ └── Contents/ (header.xml, section0.xml, content.hpf)
│ ├── gonmun/ # 공문 오버레이 (header.xml, section0.xml)
│ ├── report/ # 보고서 오버레이
│ ├── minutes/ # 회의록 오버레이
│ └── proposal/ # 제안서/사업개요 오버레이 (색상 헤더바, 번호 배지)
├── examples/
│ ├── 01_basic_document.sh # XML로 기본 문서 빌드
│ ├── 02_gonmun_example.sh # 공문 템플릿 사용
│ ├── 03_report_with_table.sh # 표 포함 보고서
│ ├── 04_read_and_extract.py # 기존 문서 읽기/추출
│ ├── 05_edit_existing.sh # unpack→편집→pack
│ ├── sample_section0.xml # 주석 달린 section0 예제
│ └── sample_header.xml # 주석 달린 header 예제
└── references/
└── hwpx-format.md # OWPML XML 요소 레퍼런스
워크플로우 1: XML-first 문서 생성 (주 워크플로우)
What ships with it
45 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.
- examples/01_basic_document.py 1.1 KB runs code
- examples/01_basic_document.sh 4.6 KB runs code
- examples/02_gonmun_example.sh 822 B runs code
- examples/02_table_document.py 1.1 KB runs code
- examples/03_multi_table_report.py 2.2 KB runs code
- examples/03_report_with_table.sh 13 KB runs code
- examples/04_read_and_extract.py 1.4 KB runs code
- examples/05_edit_existing.sh 1.3 KB runs code
- examples/06_memo_document.py 1.3 KB runs code
- examples/07_from_data.py 3.5 KB runs code
- examples/activity_report.hwpx 10 KB
- examples/business_overview.hwpx 9.9 KB
- examples/expense_report.hwpx 10 KB
- examples/sample_header.xml 15 KB
- examples/sample_input.json 1.2 KB
- examples/sample_input.md 582 B
- examples/sample_section0.xml 12 KB
- examples/service_agreement.hwpx 9.8 KB
- references/hwpx-format.md 8.3 KB
- scripts/analyze_template.py 15 KB runs code
- scripts/build_hwpx.py 8.3 KB runs code
- scripts/create_document.py 6.7 KB runs code
- scripts/office/pack.py 1.9 KB runs code
- scripts/office/unpack.py 1.9 KB runs code
- scripts/text_extract.py 2.6 KB runs code
- scripts/validate.py 3.1 KB runs code
- templates/base/Contents/content.hpf 1.8 KB
- templates/base/Contents/header.xml 50 KB
- templates/base/Contents/section0.xml 3.7 KB
- templates/base/META-INF/container.rdf 867 B
- templates/base/META-INF/container.xml 481 B
- templates/base/META-INF/manifest.xml 118 B
- templates/base/mimetype 19 B
- templates/base/Preview/PrvImage.png 4.4 KB
- templates/base/Preview/PrvText.txt 2 B
- templates/base/settings.xml 267 B
- templates/base/version.xml 294 B
- templates/gonmun/header.xml 59 KB
- templates/gonmun/section0.xml 8.5 KB
- templates/minutes/header.xml 59 KB
- templates/minutes/section0.xml 19 KB
- templates/proposal/header.xml 64 KB
- templates/proposal/section0.xml 18 KB
- templates/report/header.xml 73 KB
- templates/report/section0.xml 10 KB
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.
- 8d ago First seen · 523 lines · 42 tokens per session scan A c3f4330fe161
hwpx is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 6,612 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.