What is korean-firefighter-law-mcp CLAUDE.md?

A set of Claude Code instructions for a Korean firefighter-law MCP project. The instructions require answers to be based on checked repository files and tool results, with evidence such as file and line references.

Use it when working on this project to guide code investigation, MCP tool use, evidence-based answers, and task boundaries.

It reduces guesses about the code, external law APIs, environment settings, and whether commands or tests actually worked.

How ssd7830-cmyk/korean-firefighter-law-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ssd7830-cmyk/korean-firefighter-law-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ssd7830-cmyk/korean-firefighter-law-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ssd7830-cmyk/korean-firefighter-law-mcp

Made for: Claude Code.

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/instructions/ssd7830-cmyk/korean-firefighter-law-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ssd7830-cmyk/korean-firefighter-law-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ssd7830-cmyk/korean-firefighter-law-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ssd7830-cmyk/korean-firefighter-law-mcp/claude-md/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/instructions/ssd7830-cmyk/korean-firefighter-law-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ssd7830-cmyk/korean-firefighter-law-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 962 This file is loaded in full into every session.

When invoked 962 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00962	$0.00962
Opus 5	$0.00481	$0.00481
Sonnet 5	$0.00192	$0.00192
Haiku 4.5	$0.00096	$0.00096

Measured 12d ago against content hash 1a63a1a0dec1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

korean-firefighter-law-mcp CLAUDE.md 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.

CLAUDE.md · 44 lines

What it actually says

korean-firefighter-law-mcp

A. 답변 규칙 — 기억이 아니라 이 저장소의 코드가 근거다

이 프로젝트에 대한 모든 사실 진술은 방금 읽은 파일이나 방금 실행한 명령의 출력만 근거로 삼는다. 기억·추측·"보통 이렇다"로 답하지 않는다. 아래는 예외 없이 적용한다.

읽기 전 단언 금지. 도구 개수, 파일 경로, 함수 시그니처, 환경변수 이름, 오퍼레이션명, 테스트 개수, 버전을 말하기 전에 해당 파일을 Read하거나 grep한다. 세션 앞부분에서 읽었더라도 그 뒤에 파일이 바뀌었을 수 있으므로 다시 확인한다.
근거 표기. 코드 관련 답에는 파일:줄 형식으로 근거를 붙인다 (예: src/tool-registry.ts:36). 근거를 댈 수 없으면 그 문장은 쓰지 않는다.
동작 주장은 실행으로만. "된다/고쳤다/통과한다"는 npm run verify(또는 해당 명령)를 실제로 돌린 출력이 있을 때만 쓴다. 실행하지 않았으면 "실행하지 않아 미확인"이라고 쓴다.
외부 API 스펙은 문서·실호출이 근거. 오퍼레이션명·파라미터명·응답 필드명을 추측하지 않는다. 활용가이드 문서나 실제 응답으로 확인한다. (추측했다가 전부 틀렸던 이력이 기준.md에 있다.)
모르면 모른다고 한다. 확인할 방법이 없으면 "확인 불가"라고 답하고, 확인하려면 무엇이 필요한지 적는다. 그럴듯한 문장으로 빈칸을 메우지 않는다.
환경 상태도 확인 대상. 서버가 떠 있는지, 키가 설정됐는지, 빌드가 최신인지는 명령으로 확인한 뒤 말한다.

이 규칙은 프로그램이 사용자에게 지키는 원칙(조회 없이 답변 생성 금지)과 같다. 개발 과정에서도 동일하게 적용한다.

B. MCP 도구 사용

이 저장소는 .mcp.json으로 자기 자신을 MCP 서버(firefighter-law)로 등록한다. 도구가 붙어 있으면 소방 법령·통계·위험물 질문은 기억으로 답하지 말고 해당 도구를 호출해서 답한다.

도구가 반환한 원문을 근거로만 답하고, 요약할 때도 원문에 없는 조문·수치를 만들지 않는다.
도구 호출이 실패하면 실패했다고 말한다. 기억으로 대체하지 않는다.
키(DATA_GO_KR_KEY, LAW_OC)는 셸 환경변수로 주입된다. 없으면 도구가 발급 안내 오류를 반환한다.

C. 작업 규칙

요청 안 한 기능 만들지 않기. 같은 결과면 짧은 쪽. 다 만든 뒤 빼도 되는 코드 찾아서 빼기.
결과물은 MCP 서버 + 소방관용 챗봇 페이지 1장(src/web/chat-page.ts + chat-script.ts)이다. 그 외 대시보드·프런트엔드는 만들지 않는다.
DB를 저장소에 넣지 않는다. 데이터는 API 실시간 호출 + 인메모리 캐시. SQLite는 호출 한도가 실측으로 문제 될 때만 CacheStore 구현체로 추가.
모든 도구는 src/tool-registry.ts의 allTools[]에만 등록한다. 의존 방향: tools → lib → (fetch). 역방향 금지.
파일당 200줄 미만, 단일 책임.
인증키는 환경변수(DATA_GO_KR_KEY, LAW_OC)로만. 에러·로그에 키가 노출되지 않게 maskSensitiveUrl을 거친다.
stdout은 MCP 프로토콜 전용 — 로그는 반드시 stderr.
확정된 의도·검증 기준은 기준.md에 기록하고, 증거 없이 "된다"고 표시하지 않는다 (미확인은 미확인으로).

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.

12d ago First seen · 44 lines · 962 tokens per session scan A 1a63a1a0dec1

Subscribe to this mod's changes

korean-firefighter-law-mcp CLAUDE.md is an instructions file published in the GitHub repository ssd7830-cmyk/korean-firefighter-law-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 962 tokens to every session, about $0.0048 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.

Legal and compliance anthropic claude fire-safety korea korean legal-tech

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

korean-firefighter-law-mcp: Instructions file for Claude Code