Borrowing it
Nothing to install: this file belongs to wujinkim/korea-business-verify. 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/wujinkim/korea-business-verify/main/CLAUDE.mdgit clone --depth 1 https://github.com/wujinkim/korea-business-verifyWrote 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/wujinkim/korea-business-verify/claude-md)<a href="https://agentmods.dev/instructions/wujinkim/korea-business-verify/claude-md"><img src="https://agentmods.dev/badge/instructions/wujinkim/korea-business-verify/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/wujinkim/korea-business-verify/claude-md"><img src="https://agentmods.dev/badge/instructions/wujinkim/korea-business-verify/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 | $0.00730 | $0.00730 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
korea-business-verify 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
kr-biz-verify — 프로젝트 규칙
한국 사업자 검증 액션 MCP 서버. SSOT는 kr-biz-verify-mcp-plan.md(작업계획서) — 모든 작업은 계획서의 루프(Loop 0~8) 순서와 각 루프의 AC(수용 기준)를 따른다. 계획서와 충돌하는 판단은 하지 말고 보고한다.
역할 분담 — 구현과 평가의 분리
- 이 세션(zai/GLM)은 구현 담당이다. 평가는 별도 세션(Claude)이 수행한다.
- 평가가 가능하도록, 루프 단위 작업 완료 시
docs/PROGRESS.md에 기록한다: 루프 번호 · 수행 내용 · AC 충족 증거(실행한 명령과 실제 출력) · 미해결 이슈. - "되는 것처럼 보임"으로 멈추지 않는다. AC는 명령 출력으로 증명한다.
KB(지식그래프) 사용 — 필수
kb MCP 도구(kb_search / kb_get / kb_upsert)를 사용한다.
- 작업 시작 전
kb_search로 관련 지식을 확인한다 (query 예: "kr-biz-verify", "국세청 API"). - 루프를 넘어 유지할 가치가 있는 결정·발견·함정은
kb_upsert로 저장한다:domain은kr-biz-verify고정 (Domain 노드 이미 존재).- 8타입(Fact/Convention/Decision/Component/Domain 등)·8관계 고정 온톨로지만 사용, raw Cypher 금지.
- 저장 전 dedup: 유사 노드가 있으면 새로 만들지 말고 갱신, 모순은 SUPERSEDES 처리.
- 일회성 디버깅 로그·코드로 알 수 있는 내용은 저장하지 않는다.
도메인 불변 원칙 (계획서 §1.2 — 위반 금지)
- 개인정보 무저장: 대표자명 등 진위확인 입력값은 요청 즉시 폐기. 로그·캐시·에러 메시지 어디에도 남기지 않는다. 캐시 가능한 것은 사업자번호와 상태조회 결과뿐.
- 캐시: 상태조회 24h TTL. 진위확인은 캐시 금지.
- 모든 도구 반환은 zod 스키마 고정. 판정(
check_invoice_eligibility)에는 반드시basis(근거 필드) 동봉. - 면책 문구 상시 포함: "국세청 공공데이터 기준, 법적 효력 있는 증명은 홈택스 발급 문서 참조".
- 사업자번호는 국세청 호출 전 체크섬 형식 검증으로 걸러낸다.
- 서비스키는
.env로만 관리. 코드·로그·커밋에 노출 금지.
문서/코드 규칙
- 문서는 한국어 우선(README.md 한국어, README-EN.md 병기).
- TypeScript + MCP SDK(@modelcontextprotocol/sdk).
- 계획서에 없는 추상화·설정성·방어코드를 추가하지 않는다. 최소 코드로 푼다.
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 · 32 lines · 730 tokens per session scan A 577ed2278f0c
korea-business-verify CLAUDE.md is an instructions file published in the GitHub repository wujinkim/korea-business-verify (0 stars, last pushed 2mo ago), licensed MIT. It adds 730 tokens to every session, about $0.0036 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).