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 agentmods add instructions/hlucent/realestate-mcp/claude-mdgit clone --depth 1 https://github.com/hlucent/realestate-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/hlucent/realestate-mcp/claude-md)<a href="https://agentmods.dev/instructions/hlucent/realestate-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/realestate-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.00848 | $0.00848 |
| Opus 5 | $0.00424 | $0.00424 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
realestate-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 4d 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
CLAUDE.md — 이 프로젝트에서 작업하는 Claude를 위한 지침
이 파일은 세션 시작 시 가장 먼저, 그리고 유일하게 읽어야 하는 파일이다. 과거 대화나 전체 소스를 다시 훑지 말고, 이 문서 + 필요한 개별 파일만 열어서 작업할 것.
프로젝트 한 줄 요약
국토교통부 실거래가 공공데이터(data.go.kr) 9종 API를 MCP 도구로 감싸는 서버. 매매/전월세 × (단독다가구/아파트/연립다세대/오피스�텔) 조합.
토큰 절약 원칙 (중요)
- API 원문 PDF/기술문서를 통째로 읽지 말 것. 스펙 요약은
docs/api-spec/*.md에 이미 표로 정리되어 있음. 새 필드 추가 등 진짜 원문 확인이 필요할 때만 원본 참조. - 매 세션 전체 git log를 훑지 말 것. 최근 상태는
docs/devlog/의 가장 최신 파일 하나만 보면 충분하다 (누적 로그가 아니라 스냅샷 방식). - 소스 전체를 view하지 말고
src/client.ts(공통 로직)와 지금 작업할src/tools/xxx.ts파일만 연다. 8개 tools 파일은 서로 거의 동일한 패턴이므로 1개를 참고 템플릿으로 삼아 나머지를 유추해 작성하면 됨(전부 열어볼 필요 없음). - 응답은 항상 결론(변경 요약)부터 — 사용자 지침(userPreferences)의 두괄식 원칙 준수.
아키텍처 (자세한 설계는 docs/ARCHITECTURE.md)
src/client.ts: serviceKey 조립, XML→JSON 파싱, 에러코드(01~32) 매핑 — 공통 1개src/tools/*.ts: 8개 도구, 각자 endpoint URL + 응답 필드 스키마(zod)만 다름src/config.ts: endpoint URL 상수 (serviceKey는 여기 없음)src/keyContext.ts: AsyncLocalStorage로 요청별 serviceKey 격리 (아래 배포 방식 참고)src/index.ts: Express + StreamableHTTPServerTransport 기반 HTTP MCP 서버 (/mcp)
배포 (Fly.io)
- https://realestate-mcp-hlucent.fly.dev/mcp 로 배포됨. seoul-air-quality-mcp,
construction-alert-mcp와 동일한 패턴: serviceKey를 서버 환경변수/Fly secrets로
저장하지 않고, 요청마다
?key=...쿼리 파라미터로 받아 AsyncLocalStorage에 격리 보관한다 (src/keyContext.ts). 서버 프로세스 자체는 키를 모른다. - 배포는
.\deploy.ps1 -CommitMessage "..."(커밋→push→flyctl deploy→smoke test 자동화, construction-alert-mcp/deploy.ps1과 동일 구조).
현재 진행 상태
→ docs/devlog/에서 파일명 날짜순 가장 마지막 항목 확인. (예: 2026-08-07.md)
작업 규칙
- 새 기능/수정 완료 시 반드시
docs/devlog/YYYY-MM-DD.md를 자동 생성/갱신할 것 (형식은docs/devlog/_TEMPLATE.md참고). 사용자가 수동으로 안 씀. - 커밋 메시지는
feat:,fix:,docs:,refactor:등 conventional commits 형식. - serviceKey는 코드/커밋에 절대 포함 금지 (.env, .gitignore 처리됨).
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.
- 4d ago First seen · 43 lines · 848 tokens per session scan A 1daa1ac1a2b1
realestate-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/realestate-mcp (0 stars, last pushed 13d ago), licensed MIT. It adds 848 tokens to every session, about $0.0042 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
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.
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.
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).