hwpforge-submission-check

hwpforge-submission-check is a skill for Claude Code from ai-screams/HwpForge. It costs 172 tokens per session (4,362 once invoked), scanned A, original, Apache-2.0.

A report-only check for Korean HWPX documents, the modern file format used by Hancom Hangul word-processing software, before they are submitted or sent. It checks whether a filled form, application, or report appears complete without changing the original file.

In plain words
What is it for?
Use it to check a final HWPX form, application, or report before submission or delivery, including a legacy HWP file after converting it to HWPX.
Why use it?
It helps identify missing information or submission problems while preserving the document. It also makes clear which checks could not be performed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to check a final HWPX form, application, or report before submission or delivery, including a legacy HWP file after converting it to HWPX.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai-screams/hwpforge/hwpforge-submission-check
Install

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.

Any agent
npx skills add ai-screams/HwpForge --skill hwpforge-submission-check
Clone the repo
git clone --depth 1 https://github.com/ai-screams/HwpForge

Made for: Claude Code.

Wrote 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.

agentmods badge for hwpforge-submission-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-screams/hwpforge/hwpforge-submission-check/github.svg)](https://agentmods.dev/skills/ai-screams/hwpforge/hwpforge-submission-check)
Your own site
<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.

agentmods 80×15 button for hwpforge-submission-check

Your own site · 80×15
<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>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 22d ago against content hash 10b3a67793bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/hwpforge-submission-check/SKILL.md · 148 lines

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

  1. 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.
  2. Write nothing next to the input. The script writes only into a new temp dir.
  3. 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.
  4. The script's last line decides completeness. CHECK COMPLETE (exit 0) or CHECK INCOMPLETE: <steps> (exit 1). On INCOMPLETE the verdict is 점검 불완전 — 확인 필요; name the steps and the error codes from their exit= lines; for cell-coverage, name each skipped table line. A PDF render failure is not in the gate; it only leaves the layout unverified.
  5. 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.

Read the full file on GitHub · 148 lines

Files

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.

Changes

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.

  1. 22d ago Changed 10b3a67793bf
  2. 1mo ago First seen · 148 lines · 172 tokens per session scan A cc48d63bc811

Subscribe to this mod's changes

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.