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 laguna821/Achmage-Skills --skill kordoc-workbenchgit clone --depth 1 https://github.com/laguna821/Achmage-SkillsWrote 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/laguna821/achmage-skills/kordoc-workbench)<a href="https://agentmods.dev/skills/laguna821/achmage-skills/kordoc-workbench"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/kordoc-workbench/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/laguna821/achmage-skills/kordoc-workbench"><img src="https://agentmods.dev/badge/skills/laguna821/achmage-skills/kordoc-workbench.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 | $0.00043 | $0.00648 |
| Opus 5.5 | $0.00017 | $0.00259 |
| Sonnet 5.5 | $0.00009 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- kordoc-workbench — 100% identical, 0 lines differ
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 newoutputDir. Invokenode scripts/run.mjs request.jsonorpython scripts/launch.py request.json. If Node is missing, run the platform setup script. Optional capabilities download pinned dependencies/models only when requested; explicitKORDOC_OFFLINE=1forbids downloads. Querymode: capabilitiesfor 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.
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.
- ASSETS.json 1.2 KB
- extensions/formula/package-lock.json 35 KB
- extensions/formula/package.json 147 B
- extensions/ocr/package-lock.json 8.0 KB
- extensions/ocr/package.json 135 B
- extensions/pdf/package-lock.json 9.0 KB
- extensions/pdf/package.json 162 B
- extensions/print/package-lock.json 32 KB
- extensions/print/package.json 136 B
- extensions/raster/package-lock.json 20 KB
- extensions/raster/package.json 127 B
- LICENSE-WORKBENCH 1.1 KB
- NOTICE-KORDOC 6.6 KB
- PACKAGE-MANIFEST.json 9.0 KB
- references/engine-api.d.ts 119 KB runs code
- references/gongmunseo.md 2.0 KB
- references/hanmark.md 1.3 KB
- references/operations.md 4.0 KB
- references/template-pack-v1.schema.json 3.3 KB
- references/templates.md 2.2 KB
- scripts/chunk-3T6O35FL.mjs 2.0 KB runs code
- scripts/chunk-4KEIBFBR.mjs 367 KB runs code
- scripts/chunk-ACW76YWF.mjs 83 KB runs code
- scripts/chunk-AN7BM5RT.mjs 427 B runs code
- scripts/chunk-HW7SKSEC.mjs 39 KB runs code
- scripts/chunk-IF2FUB7X.mjs 9.5 KB runs code
- scripts/chunk-NVQKGGHQ.mjs 2113 KB runs code
- scripts/chunk-PZTNOUTU.mjs 7.8 KB runs code
- scripts/chunk-VJBJ2GTC.mjs 5.7 KB runs code
- scripts/chunk-WT3MK4B4.mjs 2.0 KB runs code
- scripts/extensions.mjs 335 KB runs code
- scripts/formula-DAMFHLQO-LDM2NI7S.mjs 25 KB runs code
- scripts/hanmark-FAJO3LAV.mjs 5.1 KB runs code
- scripts/image-ocr-VH54SDZ7-F4MAU2QI.mjs 5.0 KB runs code
- scripts/install.mjs 3.3 KB runs code
- scripts/launch.py 2.6 KB runs code
- scripts/model-prepare.mjs 15 KB runs code
- scripts/page-range-M5SRB2WK-P7SYKK4R.mjs 385 B runs code
- scripts/parser-Z6PHB54O-PKRA3MAX.mjs 152 KB runs code
- scripts/pdf-ocr-JI3K7JIN-FFRWHHTW.mjs 554 B runs code
- scripts/run.mjs 22 KB runs code
- setup.ps1 1.5 KB runs code
- setup.sh 1.8 KB runs code
- templates/간이기안문_서식.hwpx 7.1 KB
- templates/간이기안문_예시값.json 542 B
- templates/일반기안문_서식.hwpx 6.7 KB
- templates/일반기안문_예시값.json 1.1 KB
- THIRD_PARTY/apache-2.0.LICENSE 11 KB
- THIRD_PARTY/claw-hwp.LICENSE 1.0 KB
- THIRD_PARTY/hml-equation-parser.LICENSE 11 KB
- THIRD_PARTY/hml-equation-parser.txt 1.5 KB
- THIRD_PARTY/opendataloader-pdf.txt 1.2 KB
- THIRD_PARTY/pix2text.txt 814 B
- THIRD_PARTY/rhwp-forms.txt 1.8 KB
- THIRD-PARTY-LICENSES.txt 531 KB
- THIRD-PARTY-PACKAGES.json 59 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 · 20 lines · 43 tokens per session scan A 109952f0a1bb
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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
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.
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.