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 sonmeggy/korean-engineering-mcp --skill korean-engineering-grounded-answergit clone --depth 1 https://github.com/sonmeggy/korean-engineering-mcpWrote 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/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer)<a href="https://agentmods.dev/skills/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer"><img src="https://agentmods.dev/badge/skills/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer/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/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer"><img src="https://agentmods.dev/badge/skills/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer.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 | $0.00090 | $0.02058 |
| Opus 5.5 | $0.00036 | $0.00823 |
| Sonnet 5.5 | $0.00018 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
korean-engineering-grounded-answer 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Korean Engineering Grounded Answer
Use this skill for Korean engineering questions across water/wastewater, roads, railways, urban planning, rivers/water resources, ports/coasts, airports/aviation, architecture, structures, geotechnical, tunnels, bridges, building services, landscape, agricultural infrastructure, environment, construction management, procurement, and technical-grounding judgment.
Mandatory rule
Do not answer from general knowledge alone. Before giving a substantive answer, gather evidence using the companion MCP server whenever available:
- Run
classify_engineering_domainwhen the field is ambiguous or multidisciplinary; otherwise letgrounded_engineering_research(domain="auto")classify it. - Call
grounded_engineering_researchbefore drafting the answer. - If evidence is weak, retry with the returned
domain_contextlaw/admin-rule hints and narrower or broader Korean keywords. - Use
get_standard_detail,search_laws,get_law_detail,search_admin_rules,get_admin_rule_detail,search_interpretations, orsearch_reference_documentsto fill missing citation details. - If MCP is unavailable, use official web search or verified local reference documents before answering.
- If direct evidence is still unavailable, say
직접 근거 미확인or근거 불충분; do not make a definitive claim. - HTML is optional. Do not call
render_engineering_answer_htmlautomatically after an engineering answer. - If the user did not explicitly request HTML in the current turn, first deliver the complete Markdown answer, then ask
동일 내용의 HTML 보고서도 생성할까요?as a separate conversational prompt and wait for the reply. Never append that prompt to the engineering answer body. - An explicit HTML request in the current turn or an affirmative reply is confirmation. Only then call
render_engineering_answer_htmlwithuser_confirmed_html=trueand the exact final engineering Markdown body, excluding the conversational HTML opt-in prompt; a direct request does not require a second confirmation.
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.
- 2mo ago First seen · 126 lines · 90 tokens per session scan A f0423fc95b3b
korean-engineering-grounded-answer is a skill published in the GitHub repository sonmeggy/korean-engineering-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 2,058 once invoked, about $0.0004 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 2026-08-31.
korean-engineering-grounded-answer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| korean-engineering-grounded-answersonmeggy/korean-engineering-mcp | Skill | 2 | 2mo ago | MIT | A | 90 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |