kordoc-parse-document

kordoc-parse-document is a skill for Codex from composite/korean-skills. It costs 94 tokens per session (448 once invoked), scanned A, original, MIT.

A document-reading tool for converting Korean HWP, HWPX, and PDF files into readable text or structured JSON.

In plain words
What is it for?
Use it to extract document content, metadata, outlines, warnings, and page counts from a supplied local file.
Why use it?
It lets users read, summarize, or inspect Korean office documents without opening them in their original desktop applications.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to extract document content, metadata, outlines, warnings, and page counts from a supplied local file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/composite/korean-skills/kordoc-parse-document
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 composite/korean-skills --skill kordoc-parse-document
Clone the repo
git clone --depth 1 https://github.com/composite/korean-skills

Made for: Codex.

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 kordoc-parse-document

README.md
[![agentmods](https://agentmods.dev/badge/skills/composite/korean-skills/kordoc-parse-document.svg)](https://agentmods.dev/skills/composite/korean-skills/kordoc-parse-document)
Your own site
<a href="https://agentmods.dev/skills/composite/korean-skills/kordoc-parse-document"><img src="https://agentmods.dev/badge/skills/composite/korean-skills/kordoc-parse-document.svg" alt="Measured on agentmods" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 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 $0.00094 $0.00448
Opus 5 $0.00047 $0.00224
Sonnet 5 $0.00019 $0.00090
Haiku 4.5 $0.00009 $0.00045

Measured 8d ago against content hash 453851f940fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kordoc-parse-document 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.

skills/kordoc-parse-document/SKILL.md · 46 lines

What it actually says

kordoc: parse_document

Use the public CLI first. This skill maps to the parse_document intent in src/mcp.ts, but without MCP.

Input Requirements

  • Require exactly one target document.
  • Require the user to attach the document or provide a concrete local path.
  • Accept only supported formats: .hwp, .hwpx, .pdf.
  • Do not proceed if the document is missing or the path is ambiguous.

Default Command

npm exec --yes --package=kordoc --package=pdfjs-dist -- \
  kordoc /abs/path/document.hwpx

Use JSON when the caller needs blocks or metadata:

npm exec --yes --package=kordoc --package=pdfjs-dist -- \
  kordoc /abs/path/document.hwpx --format json --silent

Workflow

  1. Resolve the target file to an absolute path.
  2. Confirm the extension is .hwp, .hwpx, or .pdf.
  3. Use plain CLI output for human reading.
  4. Use --format json when the task needs metadata, outline, warnings, or blocks.
  5. Summarize the parsed content instead of dumping the whole document unless the user asked for raw output.

Guardrails

  • Install pdfjs-dist alongside kordoc; the package may fail to load without it.
  • Preserve warnings about image-based PDFs, skipped elements, or hidden text filtering.
  • Do not claim OCR happened unless the execution path explicitly used an OCR-capable custom script.
  • If the file is large, summarize key sections first.
  • Refuse to continue when no supported document was provided.
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. 8d ago First seen · 46 lines · 94 tokens per session scan A 453851f940fe

Subscribe to this mod's changes

kordoc-parse-document is a skill published in the GitHub repository composite/korean-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 448 once invoked, about $0.0005 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.