korean-engineering-grounded-answer

korean-engineering-grounded-answer is a skill for Claude Code, Codex from sonmeggy/korean-engineering-mcp. It costs 90 tokens per session (2,058 once invoked), scanned A, original, MIT.

A Korean-language workflow skill for answering engineering questions using Korean laws, construction standards, agency rules, and other cited sources. It covers fields such as roads, buildings, bridges, water, railways, and construction management.

In plain words
What is it for?
Use it to research Korean engineering requirements, distinguish applicable standards, provide grounded conclusions, and optionally create an HTML report after user confirmation.
Why use it?
It reduces unsupported answers by requiring the relevant engineering field and source evidence to be checked before giving a substantive answer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to research Korean engineering requirements, distinguish applicable standards, provide grounded conclusions, and optionally create an HTML report after user confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer
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 sonmeggy/korean-engineering-mcp --skill korean-engineering-grounded-answer
Clone the repo
git clone --depth 1 https://github.com/sonmeggy/korean-engineering-mcp

Made for: Claude Code, 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 korean-engineering-grounded-answer

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer/github.svg)](https://agentmods.dev/skills/sonmeggy/korean-engineering-mcp/korean-engineering-grounded-answer)
Your own site
<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.

agentmods 80×15 button for korean-engineering-grounded-answer

Your own site · 80×15
<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>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,058 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 $0.00090 $0.02058
Opus 5.5 $0.00036 $0.00823
Sonnet 5.5 $0.00018 $0.00412
Haiku 4.5 $0.00009 $0.00206

Measured 2mo ago against content hash f0423fc95b3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

skills/korean-engineering-grounded-answer/SKILL.md · 126 lines

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:

  1. Run classify_engineering_domain when the field is ambiguous or multidisciplinary; otherwise let grounded_engineering_research(domain="auto") classify it.
  2. Call grounded_engineering_research before drafting the answer.
  3. If evidence is weak, retry with the returned domain_context law/admin-rule hints and narrower or broader Korean keywords.
  4. Use get_standard_detail, search_laws, get_law_detail, search_admin_rules, get_admin_rule_detail, search_interpretations, or search_reference_documents to fill missing citation details.
  5. If MCP is unavailable, use official web search or verified local reference documents before answering.
  6. If direct evidence is still unavailable, say 직접 근거 미확인 or 근거 불충분; do not make a definitive claim.
  7. HTML is optional. Do not call render_engineering_answer_html automatically after an engineering answer.
  8. 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.
  9. An explicit HTML request in the current turn or an affirmative reply is confirmation. Only then call render_engineering_answer_html with user_confirmed_html=true and the exact final engineering Markdown body, excluding the conversational HTML opt-in prompt; a direct request does not require a second confirmation.

Read the full file on GitHub · 126 lines

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. 2mo ago First seen · 126 lines · 90 tokens per session scan A f0423fc95b3b

Subscribe to this mod's changes

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.

Related

korean-engineering-grounded-answer compared with skills from other repositories

korean-engineering-grounded-answer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
korean-engineering-grounded-answersonmeggy/korean-engineering-mcpSkill22mo agoMITA90Claude Code, Codex
fto-triageanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A81Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA49Claude Code
terms-of-servicegenspark-ai/genofficeSkill12k2d agoApache-2.0A32Claude Code, Codex
x-scorecardx-cmd/x-cmdSkill4.7k7d agoApache-2.0A57Claude Code, Codex
gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-rechtSkill1.8kyesterdayApache-2.0A69Claude Code