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 ai-screams/HwpForge --skill hwpforge-submission-checkgit clone --depth 1 https://github.com/ai-screams/HwpForgeWrote 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/ai-screams/hwpforge/hwpforge-submission-check)<a href="https://agentmods.dev/skills/ai-screams/hwpforge/hwpforge-submission-check"><img src="https://agentmods.dev/badge/skills/ai-screams/hwpforge/hwpforge-submission-check/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/ai-screams/hwpforge/hwpforge-submission-check"><img src="https://agentmods.dev/badge/skills/ai-screams/hwpforge/hwpforge-submission-check.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 | $0.00172 | $0.04362 |
| Opus 5.5 | $0.00069 | $0.01745 |
| Sonnet 5.5 | $0.00034 | $0.00872 |
| Haiku 4.5 | $0.00017 | $0.00436 |
Grade A, and why
hwpforge-submission-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HwpForge 제출 전 점검
Checks a .hwpx the user is about to submit and reports what is missing or should not be sent. For a legacy .hwp, convert it first into a new temp dir, never next to the input (d=$(mktemp -d) && hwpforge convert-hwp5 old.hwp -o "$d/old.hwpx" && echo "$d/old.hwpx"), check that .hwpx, and delete $d after the report.
Rules
- Report only. Never modify, re-save or replace the input. If the user wants fixes, hand off to the main hwpforge skill after the report.
- Write nothing next to the input. The script writes only into a new temp dir.
- HwpForge surfaces only. Do not unzip the package or grep its XML; the script runs every check. What it cannot see is listed under 알려진 한계: report it as not checked, do not work around it.
- The script's last line decides completeness.
CHECK COMPLETE(exit 0) orCHECK INCOMPLETE: <steps>(exit 1). On INCOMPLETE the verdict is 점검 불완전 — 확인 필요; name the steps and the error codes from theirexit=lines; forcell-coverage, name eachskipped tableline. A PDF render failure is not in the gate; it only leaves the layout unverified. - Plain Korean, no raw JSON. The user gets the report format at the end, nothing else.
Step 1: run the script once
bash ${CLAUDE_SKILL_DIR}/scripts/check.sh /path/to/doc.hwpx
It takes exactly one argument and runs the hwpforge found on PATH; any other argument count stops it with CHECK INCOMPLETE: usage. If hwpforge is not on PATH, ask the user to install it or add it to PATH. Run it through bash with exactly this path; the skill's pre-approval matches only this form. Everything the verdict needs is printed; the temp dir is deleted when the script ends. To read the full outputs (paras.txt, doc.json, plan.json) or keep the rendered doc.pdf for the visual check, run KEEP=1 bash ${CLAUDE_SKILL_DIR}/scripts/check.sh … (this form asks for permission): it prints scratch: DIR (kept), and you delete that dir when done.
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.
- 22d ago Changed 10b3a67793bf
- 1mo ago First seen · 148 lines · 172 tokens per session scan A cc48d63bc811
hwpforge-submission-check is a skill published in the GitHub repository ai-screams/HwpForge (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 172 tokens to every session and 4,362 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
kordoc
A command-line and server tool for reading and creating Korean official documents, including HWP, HWPX, PDF, DOCX, and spreadsheet files. It can convert documents to Markdown and create or update HWPX files.
processing-markdown
Processes Markdown files using mq, a jq-like query language for Markdown. Use when the user mentions Markdown processing, content extraction, document transformation, or mq queries.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Read, extract, split, merge, rotate, watermark, fill, OCR, or create PDF files with verification of page counts and text extraction.
docx
Create/edit/inspect Word documents using available managed or host capabilities.
pptx
Create/edit/inspect/verify slide decks and PPTX presentations.