Borrowing it
Nothing to install: this file belongs to paeyoungpark-web/lupa-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/paeyoungpark-web/lupa-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/paeyoungpark-web/lupa-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/paeyoungpark-web/lupa-mcp/claude-md)<a href="https://agentmods.dev/instructions/paeyoungpark-web/lupa-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paeyoungpark-web/lupa-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/paeyoungpark-web/lupa-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/paeyoungpark-web/lupa-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 | $0.00828 | $0.00828 |
| Opus 5 | $0.00414 | $0.00414 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
lupa-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 10d 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 — lupa-mcp 개발 노트
최종 갱신: 2026-08-26. Lupa 앱: https://lupa.kr
무엇인가
Lupa가 번들로 동봉하는 CLI(lupa-search)를 감싸는 로컬 stdio MCP 서버.
어느 MCP 클라이언트에서든 Mac의 문서를 파일명·내용으로 찾게 해준다.
- 도구 둘:
lupa_search(검색) ·lupa_read(인덱스 본문 = CLI의--content) - Node ESM +
@modelcontextprotocol/sdk, npm 배포(npx -y lupa-mcp) - 스모크 테스트:
node test/smoke.js [검색어]— 실제 클라이언트처럼 stdio로 말을 건다
설계 규칙 (어기지 말 것)
- 여기서 인덱싱하지 않는다. 이 서버는 앱이 만든 인덱스를 읽기만 한다. 자체 인덱서를 넣으면 이 도구 자체가 전체 디스크 접근 권한을 요구하게 되는데, 그러면 "에이전트에게 디스크 권한을 주지 않고도 문서 내용을 쓴다"는 이 프로젝트의 존재 이유가 사라진다.
- 원격/호스팅 변형을 만들지 않는다. 인덱스는 사용자 Mac에 있고, Lupa에는 네트워크 코드가 없다. stdio 로컬 전용을 유지한다.
- 실행 파일 경로를 하드코딩하지 않는다. 항상
src/cli.js의findLupaSearch()로 탐색한다:LUPA_SEARCH_PATH→/Applications/Lupa.app→~/Applications→Lupa-dev.app→/usr/local/bin→/opt/homebrew/bin. 하드코딩하면 사용자마다 다른 설치 위치와 옛 인덱스를 보게 된다. - 결과 필드를 늘릴 때는 토큰 비용을 먼저 생각한다. 에이전트에게 보내는 모든 글자가
비용이다.
trimResult()가 필드를 줄이고 스니펫을 자른다.
알아둘 사실
--content는 Lupa 1.1부터 있다. 그 이전 버전에 넘기면 종료 코드 64(알 수 없는 플래그)가 떨어진다.supportsContent()가--help를 한 번 훑어 캐시하고, 없으면 업데이트 안내를 낸다.- CLI 종료 코드 계약:
0정상 ·1검색 실패 ·2인덱스 없음 ·3본문 없음 ·64인자 오류.src/cli.js의EXIT_MESSAGES가 사람 말로 옮긴다. - 검색 문법 치트시트를 도구 설명에 박아 넣었다(
QUERY_SYNTAX). Claude Code 플러그인은 스킬 파일로 가르치지만 다른 클라이언트에는 스킬이 없다. 앱의 문법이 바뀌면 여기도 고칠 것. - 무료 Lupa 인덱스는 파일 5만 개까지다. 이 서버는 앱이 인덱싱한 만큼만 볼 뿐, 여기에 별도 제한이나 과금은 없다.
상태
- 스모크 테스트 6개 통과 (App Store판과 개발 빌드 양쪽에서 확인)
- npm 미배포. 배포 전:
npm login→npm publish
다음
- npm 배포
- Lupa 1.1 출시 후
lupa_read실동작 재확인 - lupa.kr에 설치 안내 반영
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.
- 10d ago First seen · 50 lines · 828 tokens per session scan A 9b0383a3c254
lupa-mcp CLAUDE.md is an instructions file published in the GitHub repository paeyoungpark-web/lupa-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 828 tokens to every session, about $0.0041 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).