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 composite/korean-skills --skill kordoc-compare-documentsgit clone --depth 1 https://github.com/composite/korean-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/composite/korean-skills/kordoc-compare-documents)<a href="https://agentmods.dev/skills/composite/korean-skills/kordoc-compare-documents"><img src="https://agentmods.dev/badge/skills/composite/korean-skills/kordoc-compare-documents/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/composite/korean-skills/kordoc-compare-documents"><img src="https://agentmods.dev/badge/skills/composite/korean-skills/kordoc-compare-documents.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 | $0.00075 | $0.00548 |
| Opus 5 | $0.00037 | $0.00274 |
| Sonnet 5 | $0.00015 | $0.00110 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
kordoc-compare-documents 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 12d 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.
What it actually says
kordoc: compare_documents
Reproduce the compare_documents logic from src/mcp.ts with the public compare export.
Input Requirements
- Require exactly two target documents.
- Require the user to attach both documents or provide two concrete local paths.
- Accept only supported formats:
.hwp,.hwpx,.pdf. - Do not proceed if either document is missing.
- Preserve the user-provided ordering so source and target are not swapped implicitly.
Command
npm exec --yes --package=kordoc --package=pdfjs-dist -- node <<'SCRIPT'
const p = require("path"), fs = require("fs");
const nmBin = process.env.PATH.split(p.delimiter).find(d => d.endsWith(".bin"));
const kUrl = "file:///" + p.join(p.resolve(nmBin, ".."), "kordoc", "dist", "index.js").split(p.sep).join("/");
import(kUrl).then(async (k) => {
const fileA = "/abs/path/old.hwpx";
const fileB = "/abs/path/new.hwpx";
const rawA = fs.readFileSync(fileA);
const rawB = fs.readFileSync(fileB);
const bufA = rawA.buffer.slice(rawA.byteOffset, rawA.byteOffset + rawA.byteLength);
const bufB = rawB.buffer.slice(rawB.byteOffset, rawB.byteOffset + rawB.byteLength);
const result = await k.compare(bufA, bufB);
console.log(JSON.stringify(result, null, 2));
}).catch(e => { console.error(e); process.exit(1); });
SCRIPT
Workflow
- Resolve both files to absolute paths.
- Run
compare. - Read
statsfirst:added,removed,modified,unchanged. - Summarize the major deltas instead of repeating unchanged blocks.
- Keep source and target ordering explicit.
Guardrails
- Call out when the comparison is cross-format.
- Do not overstate semantic meaning from block-level diffs.
- Separate added, removed, and modified content in the final explanation.
- Refuse to continue when fewer than two supported documents were provided.
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.
- 12d ago First seen · 52 lines · 75 tokens per session scan A eac8656234d5
kordoc-compare-documents is a skill published in the GitHub repository composite/korean-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 548 once invoked, about $0.0004 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.
Other skills, from other repositories
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
invoice-document-pdf
Generating invoices, contracts, forms, receipts, and business documents as professional PDFs.
report-generation
Creating structured PDF reports from data, templates, and AI-generated content using professional toolchains.
md-to-pdf
Convert Markdown to styled PDFs with Mermaid diagrams, LaTeX/KaTeX math, tables, and code highlighting. Triggers on: "convert markdown to pdf", "make a pdf from this md", "export markdown as pdf", "pdf from markdown with equations".
arxiv-preflight
Pre-submission validation audit for arXiv papers across TeX source, PDF, figures, metadata, bibliography, file organization, and common-error scans. Produces pass/fail report with specific fixes per arXiv requirement. Triggers on: "check my arXiv submission", "validate for arXiv", "arXiv preflight", "ready for arXiv"…
markdown-to-pdf
Converting Markdown to professional PDFs using Pandoc, WeasyPrint, ReportLab, and related tools.