Borrowing it
Nothing to install: this file belongs to hlucent/airkorea-statistics-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/hlucent/airkorea-statistics-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/hlucent/airkorea-statistics-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/airkorea-statistics-mcp/claude-md)<a href="https://agentmods.dev/instructions/hlucent/airkorea-statistics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/airkorea-statistics-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/hlucent/airkorea-statistics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/airkorea-statistics-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 | $0.02222 | $0.02222 |
| Opus 5.5 | $0.00889 | $0.00889 |
| Sonnet 5.5 | $0.00444 | $0.00444 |
| Haiku 4.5 | $0.00222 | $0.00222 |
Grade A, and why
airkorea-statistics-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 2mo 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — airkorea-statistics-mcp 개발 지침 (Claude Code용)
0. 시작 전 필독
DEVPLAN.md 하나만 먼저 읽고 시작한다. 다른 문서는 재탐색하지 않는다. 웹서치 금지 — API 스펙은 DEVPLAN.md에 이미 있다.
1. 절대 규칙
- DEVPLAN.md 하나만 먼저 읽고 시작. 다른 문서 재탐색 금지.
- 웹서치 금지.
- 불확실하면 추측성 재설계 대신 기본값 1개로 구현 후 DEVLOG.md에 "확인 필요"로 기록.
- 동일 오류 최대 3회까지만 재시도. 3회 실패 시 기록하고 사용자에게 보고.
- 역할은 "코드 구현 + 로컬 실측 테스트"까지다.
fly launch,fly secrets set,flyctl deploy,fly logs등 fly.io 관련 명령은 절대 스스로 실행하지 않는다. - 배포 준비(코드 구현, 로컬 테스트, git commit/push)가 끝나면 아래 "작업 순서"의 정지 시점에서 멈추고, 사용자에게 PowerShell에서 배포를 진행하라고 안내한다.
2. 기술적으로 반드시 적용할 것 (과거 실패 원인 → 재발 방지)
2-1. .env 관련
BOM 문제로 python-dotenv가 키를 못 읽었던 사례가 있음. .env는 항상 UTF-8(BOM 없음)로
저장한다.
2-2. stateless_http=True 필수
mcp.run(transport="streamable-http", host="0.0.0.0", port=port, stateless_http=True)
이 옵션 없이 배포하면 Claude.ai 커넥터에서 "사용 가능한 도구 없음"으로 보이는 문제가 발생했던 전례가 있으므로 절대 빠뜨리지 않는다.
2-3. 응답 파싱은 JSON 우선, XML 폴백 필수
에러 응답이 returnType=json 요청에도 XML로 돌아올 수 있다 (1·2단계 실측 확인).
response.json()이 ValueError를 던지면 정규식으로 <CODE>/<MESSAGE> 또는
<resultCode>/<resultMsg> 패턴을 추출하는 폴백을 반드시 구현한다.
2-4. 숫자 필드는 항상 안전하게 변환
def _safe_float(v):
if v is None or v in ("", "-"):
return None
try:
return float(v)
except (ValueError, TypeError):
return None
이 서비스(ArpltnStatsSvc)는 결측과 실측 0을 구분해야 하는 대기질 데이터이므로,
0 대신 None을 반환하는 것을 기본으로 한다. 실측 결과에 따라 조정.
2-5. IP 추출 — Fly-Client-IP 우선
def _get_client_ip(request: Request) -> str:
fly_client_ip = request.headers.get("fly-client-ip")
if fly_client_ip:
return fly_client_ip.strip()
forwarded = request.headers.get("x-forwarded-for")
if forwarded:
return forwarded.split(",")[0].strip()
return request.client.host if request.client else "unknown"
2-6. CORS preflight(OPTIONS)는 rate limit 카운터에서 제외
class RateLimitMiddleware(BaseHTTPMiddleware):
async def dispatch(self, request: Request, call_next):
if request.method == "OPTIONS":
return await call_next(request)
# ... 이하 카운팅 로직
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.
- 2mo ago First seen · 196 lines · 2,222 tokens per session scan A 1f1b33c41720
airkorea-statistics-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/airkorea-statistics-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,222 tokens to every session, about $0.0089 per session on Opus 5.5. 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.
airkorea-statistics-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| airkorea-statistics-mcp CLAUDE.mdhlucent/airkorea-statistics-mcp | Instructions file | 0 | 2mo ago | MIT | A | 2,222 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | yesterday | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |