What is kordoc-workbench?

A tool for analysing Korean HWP and HWPX forms and creating HWPX reports from Markdown in a matching style. HWPX is a Korean word-processing document format, and Markdown is plain text with simple formatting marks.

It helps inspect reference forms, reuse templates, fill fixed forms, create official-style reports, and produce previews for validation.

It reduces the manual work of understanding fixed forms and reproducing their layout, while checking generated documents and reporting partial or skipped work.

kordoc-workbench — Skill for Claude Code by laguna821/Achmage-Skills

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 laguna821/Achmage-Skills --skill core

Clone the repo

git clone --depth 1 https://github.com/laguna821/Achmage-Skills

Made for: Claude Code.

Or install hallym-kordoc, the plugin that ships this one along with the rest of its 2 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/laguna821/achmage-skills/core/github.svg)](https://agentmods.dev/skills/laguna821/achmage-skills/core)

Your own site

<a href="https://agentmods.dev/skills/laguna821/achmage-skills/core"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/core/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/laguna821/achmage-skills/core"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 648 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.00648
Opus 5.5	$0.00017	$0.00259
Sonnet 5.5	$0.00009	$0.00130
Haiku 4.5	$0.00004	$0.00065

Measured 6d ago against content hash 109952f0a1bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kordoc-workbench 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 6d ago.

The scan reads SKILL.md. This mod also ships 24 executable files (references/engine-api.d.ts, scripts/chunk-3T6O35FL.mjs, scripts/chunk-4KEIBFBR.mjs, …), 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.

Origin

This is a copy

100% identical to kordoc-workbench — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

Hallym-Documents/hallym-kordoc/core/SKILL.md · 20 lines

What it actually says

Use the bundled kordoc 4.18.13 engine for Korean reports. The normal workflow is reference form → style/field analysis → confirmed Markdown → HWPX → validation and SVG/HTML preview. Keep reusable TemplatePacks with the output. Core HWP/HWPX work needs Node >=20, without OCR models or a browser.

Read references/templates.md for reference-form reports and references/gongmunseo.md for official reports. Select a mode from references/operations.md. Read other mode details only when needed. The pinned API types are in references/engine-api.d.ts.
Write a JSON request with schemaVersion: 1, mode, absolute input paths and a new outputDir. Invoke node scripts/run.mjs request.json or python scripts/launch.py request.json. If Node is missing, run the platform setup script. Optional capabilities download pinned dependencies/models only when requested; explicit KORDOC_OFFLINE=1 forbids downloads. Query mode: capabilities for environment readiness. Never treat readiness as successful document verification.
Review JSON results. Exit codes: 0 complete, 2 partial, 1 failed. Describe skipped edits/fields and requested features that were not processed. A partial result is not complete success.
Deliver output files and relevant previews. HWPX structure validation is automatic for new files; visual review and Hancom opening are separate checks.

Do not request PDF/PNG/OCR for every report. Prefer SVG/HTML previews; request expensive formats only when needed. Preserve original font names; a preview can substitute installed fonts and is not proof of exact Hancom pagination. Internet access and cache persistence vary in web sessions: disclose an unavailable extension and never silently omit a requested output.

For fixed-layout forms, use fill (HWPX preserve) or patch (HWP5/HWPX). For reports with new structure or length, use template-analyze then template-apply. Confirm role meaning from extracted XML evidence; mark non-HWPX style inference as inferred.

Freeze cover dates explicitly with frozenDate or gongmun.cover.date. Determinism applies to frozen Markdown/options/assets and engine 4.18.13, not to the AI's draft. Retain originals and use new output directories. Masking covers detected text, with image PII coverage reported separately.

In web sessions set KORDOC_WEB=1 before invoking the runner. TemplatePacks are download artifacts: reuse across sessions requires saving and reattaching the pack, or verifying its persistent storage. HanMark delivery is an optional local addon; read references/hanmark.md only when requested. Web processing runs inside the web session and must not call a PC or external processing server.

Files

What ships with it

56 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.

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.

6d ago First seen · 20 lines · 43 tokens per session scan A 109952f0a1bb

Subscribe to this mod's changes

kordoc-workbench is a skill published in the GitHub repository laguna821/Achmage-Skills (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 43 tokens to every session and 648 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to kordoc-workbench, differing in 0 lines, and is treated as a copy.

Documents Writing and docs

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…

nexu-io/open-design · 117 tokens

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…

anthropics/knowledge-work-plugins · 123 tokens

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.

JimLiu/baoyu-skills · 107 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Fetches URLs and PDFs, then summarizes or returns clean Markdown. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.

tw93/Waza · 46 tokens