Borrowing it
Nothing to install: this file belongs to LEEseungseok-01/knu-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/LEEseungseok-01/knu-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/LEEseungseok-01/knu-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/leeseungseok-01/knu-mcp/agents-md)<a href="https://agentmods.dev/instructions/leeseungseok-01/knu-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leeseungseok-01/knu-mcp/agents-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/leeseungseok-01/knu-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/leeseungseok-01/knu-mcp/agents-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 | $0.00877 | $0.00877 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
knu-mcp AGENTS.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 9d 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
AGENTS.md
강원대학교 춘천캠퍼스 공개 정보 MCP 서버. Python. (Codex/Claude Code 등 코딩 에이전트가 읽는 규칙 파일. CLAUDE.md와 동일 내용을 Codex용으로 둠.)
목표
강원대 춘천캠퍼스 공개 정보를 MCP tool로 노출. Claude Desktop/Cursor/Cline 등 MCP 클라이언트에서 자연어로 조회. 여러 tool을 조합해 "캠퍼스 브리핑" 한방 응답이 차별점.
로그인 필요한 것(수강신청·성적·도서관좌석)은 범위 밖.
스택 / 실행
- Python >=3.10, 패키지 관리
uv, 공식mcpSDK(FastMCP) - 의존성:
mcp,httpx,beautifulsoup4+ (dev)pytest. 새 의존성 추가 금지.
uv sync # 설치
uv run knu-mcp # 실행 (기본 stdio)
uv run pytest # 테스트 (네트워크 안 탐, fixture 기반)
KNU_BUS_API_KEY=<키> uv run python scripts/e2e_smoke.py # E2E (실 네트워크)
원격(HTTP) 실행: KNU_MCP_TRANSPORT=streamable-http PORT=8000 uv run knu-mcp → http://host:8000/mcp
구조
knu_mcp/
server.py # FastMCP, tool 7개 등록 (각 tool에 annotations + description에 "강원대학교 도우미")
http.py # 공용 get(10분 TTL 캐시)/post
academic.py # 학사일정 (re, scheduleData 파싱)
cafeteria.py # 학식 (POST + bs4)
notices.py # 공지 검색 (bs4, pageIndex 페이징)
shuttle.py # 두리버스 시간표/다음차 (bs4)
bus.py # 시내버스 실시간 (TAGO 공공API, httpx 직접)
tests/ # 파서 단위 테스트
scripts/e2e_smoke.py
데이터 소스 (중요 — 사이트 특성)
- 5개 tool 중 4개 = 웹 스크래핑(강원대 사이트 개편 시 깨질 수 있음), 버스만 공식 API(TAGO).
- 학사일정: 사이트가 year/month 파라미터를 무시하고 "현재 다가오는 일정"만 줌. 연간 전체 조회 불가(사이트 한계). 1회 요청.
- 공지: GET 키워드 검색·pageUnit 미지원. pageIndex 페이징만 됨 → 최근 N페이지 훑어 필터.
- 버스: 엔드포인트 반드시
https://(http는 일부 환경서 timeout). cityCode=32010, 강원대 정류소 nodeId는 bus.py 상수.
규칙 (Karpathy 4원칙 + 이 프로젝트 규약)
- Think Before Coding — 가정 명시. 애매하면 질문.
- Simplicity First — 요청한 것만. 단일 사용 코드에 추상화 금지 (ponytail).
- Surgical Changes — 건드릴 것만. 기존 스타일 따름. 바뀐 줄은 요청에 직결.
- Goal-Driven — 검증가능 목표로. 테스트 쓰고 통과까지.
프로젝트 규약:
- 외부 사이트/API 실패 시 예외 대신
{"error": "..."}반환. 크래시 금지. - 날짜
YYYY-MM-DD, 시간HH:MM. - API 키는 코드/커밋에 절대 하드코딩 금지. 환경변수
KNU_BUS_API_KEY로만. - 테스트는 네트워크 안 탐 — 저장 fixture 또는 monkeypatch.
- 새 기능은 파서 단위 테스트 먼저(TDD).
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.
- 9d ago First seen · 60 lines · 877 tokens per session scan A 5e7a259f054b
knu-mcp AGENTS.md is an instructions file published in the GitHub repository LEEseungseok-01/knu-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 877 tokens to every session, about $0.0044 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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.