Borrowing it
Nothing to install: this file belongs to whchoi98/seoul-opendata-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.
curl -O https://raw.githubusercontent.com/whchoi98/seoul-opendata-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/whchoi98/seoul-opendata-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/instructions/whchoi98/seoul-opendata-mcp/claude-md)<a href="https://agentmods.dev/instructions/whchoi98/seoul-opendata-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/whchoi98/seoul-opendata-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.
<a href="https://agentmods.dev/instructions/whchoi98/seoul-opendata-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/whchoi98/seoul-opendata-mcp/claude-md.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 | $0.00913 | $0.00913 |
| Opus 5 | $0.00456 | $0.00456 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
seoul-opendata-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 11d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context
Overview
seoul-opendata-mcp(v0.3.0, MIT)는 서울 열린데이터광장(Seoul Open Data Plaza) 실시간 도시데이터를 19개 MCP tool로 stdio를 통해 제공하는 MCP 서버입니다. GitHub: https://github.com/whchoi98/seoul-opendata-mcp.
Tech Stack
- TypeScript(strict, ESM), Node.js >=18
- @modelcontextprotocol/sdk(stdio transport), zod(입력 스키마 검증), fast-xml-parser(XML 폴백 파싱)
- vitest(단위 테스트 + 선택적 live-smoke 테스트)
Project Structure
src/client/ HTTP 클라이언트: 키 폴백, TTL 캐시, 페이지네이션, 재시도, XML 폴백, .env 로더
src/normalize/ 봉투(envelope) unwrap + 도메인별 필드 정규화
src/tools/ MCP tool 19개: 도메인 register 5개 파일 + meta/stats/health
src/data/ 핫스팟 121곳, 28개/6카테고리 데이터셋 카탈로그
tests/ vitest 스위트(단위 105+, live 4개); 픽스처=실API 캡처 불변
scripts/ capture-fixtures.ts, live-sweep.ts, setup.sh, install-hooks.sh
Key Commands
npm run build- tsc 컴파일npm run dev- tsx로src/index.ts실행npm test- vitest 스위트 실행npm run inspect- MCP Inspector 실행npm run bundle- build 후 mcpb pack/clean ->seoul-opendata-mcp.mcpbnpm run prepublishOnly- build (npm publish전 자동 실행)
Conventions
tests/fixtures/의 픽스처는 실API 캡처 결과로 불변입니다. 직접 수정하지 않고, 재캡처는scripts/capture-fixtures.ts로만 합니다(tests/CLAUDE.md참조).- 모든
normalize*함수는 출력 필드를 원본 행 필드까지 추적하는 매핑 동등성 테스트를 갖습니다. - tool 응답은
ok()봉투(src/tools/envelope.ts)를 사용합니다:{ data, asOf, source, notes }. - 외부 HTTP 호출은 모두
SeoulApiClient(src/client/seoulApi.ts)를 거칩니다 - 다른 곳에서 임의fetch호출 금지. - tool
description은 영어(2문장 이하) 다음에 한국어 순서로 작성합니다. - 커밋 접두사:
feat:fix:test:docs:chore:. - 실제 API 키를 로그나 커밋에 남기지 않습니다.
maskedKey()/maskedSubwayKey()를 사용하고,.env는 git에 커밋하지 않습니다.
Auto-Sync Rules
- 신규 tool 추가 ->
src/index.ts의TOOL_NAMES에 추가, 등록하고src/tools/CLAUDE.md를 갱신합니다. src/<module>/신규 디렉토리 생성 -> 해당 위치에CLAUDE.md를 만듭니다.- 클라이언트/정규화 계약 변경 ->
docs/reference/api.md를 갱신합니다. - 키 처리 또는 샘플 모드 동작 변경 ->
docs/reference/security.md를 갱신합니다. - tool 설명 또는 LLM 대상 문구 변경 ->
docs/reference/agent-llm.md를 갱신합니다.
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.
- 11d ago First seen · 50 lines · 913 tokens per session scan A 13741f1d17bc
seoul-opendata-mcp CLAUDE.md is an instructions file published in the GitHub repository whchoi98/seoul-opendata-mcp (1 stars, last pushed 25d ago), licensed MIT. It adds 913 tokens to every session, about $0.0046 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 instructions, from other repositories
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.
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.
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).
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.
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.
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).