Borrowing it
Nothing to install: this file belongs to hlucent/airkorea-realtime-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-realtime-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/hlucent/airkorea-realtime-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-realtime-mcp/claude-md)<a href="https://agentmods.dev/instructions/hlucent/airkorea-realtime-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/airkorea-realtime-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-realtime-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/airkorea-realtime-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 | $0.02847 | $0.02847 |
| Opus 5.5 | $0.01139 | $0.01139 |
| Sonnet 5.5 | $0.00569 | $0.00569 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
airkorea-realtime-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — airkorea-realtime-mcp
절대 규칙
- DEVPLAN.md 하나만 먼저 읽고 시작한다. 다른 문서 재탐색 금지.
- 웹서치 금지 (API 스펙은 DEVPLAN.md에 이미 있음).
- 불확실하면 추측성 재설계 대신 기본값 1개로 구현 후 DEVLOG.md에 "확인 필요"로 기록.
- 동일 오류 최대 3회까지만 재시도. 3회 실패 시 기록하고 사용자에게 보고.
- 역할은 "코드 구현 + 로컬 실측 테스트"까지다.
fly launch,fly secrets set,flyctl deploy,fly logs등 fly.io 관련 명령은 절대 스스로 실행하지 않는다. - 배포 준비(코드 구현, 로컬 테스트, git commit/push)가 끝나면 아래 "작업 순서"의 정지 시점에서 멈추고, "사용자 안내 문구"를 그대로 출력한다.
기술적으로 반드시 적용할 것
.env
BOM 없는 UTF-8로 저장한다.
# [System.IO.File]::WriteAllText(경로, "KEY=값", [System.Text.UTF8Encoding]::new($false))
server.py의 mcp.run()은 항상 stateless_http=True 포함
mcp.run(transport="streamable-http", host="0.0.0.0", port=port, stateless_http=True)
이유: fly.io는 기본 2대 머신(고가용성)을 띄우므로, 세션이 프로세스 인메모리에만 저장되면 다른 머신으로 라우팅될 때 404가 발생한다. 이 옵션 누락 시 Claude.ai 커넥터에서 "사용 가능한 도구 없음"으로 보이는 문제가 발생한 전례가 있으므로 절대 빠뜨리지 않는다.
응답 파싱: JSON 우선, XML 폴백 필수
returnType=json으로 요청해도 일부 에러 응답은 XML로 돌아올 수 있다 (다른 공공 API에서
실측 확인된 패턴). response.json()이 ValueError를 던지면 정규식으로
<resultCode>/<resultMsg> 패턴을 추출하는 폴백을 반드시 구현한다.
import re
def parse_response(text: str) -> dict:
try:
return json.loads(text)
except ValueError:
code_match = re.search(r"<resultCode>(.*?)</resultCode>", text)
msg_match = re.search(r"<resultMsg>(.*?)</resultMsg>", text)
return {
"response": {
"header": {
"resultCode": code_match.group(1) if code_match else "99",
"resultMsg": msg_match.group(1) if msg_match else "UNKNOWN_XML_RESPONSE",
}
}
}
이 API의 에러코드 체계 (DEVPLAN.md 1-6절 참고)
서울시 계열(INFO-000/ERROR-3xx)과 다른 공공데이터포털 표준 방식이다. resultCode가
"00"이 아니면 에러로 처리하고, resultMsg를 그대로 사용자에게 전달한다. HTTP status는
정상 요청/에러 요청 모두 200에 가까우므로 반드시 body의 resultCode로 판단해야 한다.
숫자/결측 필드는 항상 안전하게 변환
이 API는 결측치가 문자열 "-"로 오는 사례가 명세서 예제에서 실제로 확인되었다
(<khaiValue>-</khaiValue>). 다른 프로젝트에서 확인된 null/빈 문자열/실수(float) 패턴에
더해 이 "-" 케이스까지 처리하는 안전 변환 함수를 반드시 넣는다:
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 · 232 lines · 2,847 tokens per session scan A acf8795bf354
airkorea-realtime-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/airkorea-realtime-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,847 tokens to every session, about $0.0114 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-realtime-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| airkorea-realtime-mcp CLAUDE.mdhlucent/airkorea-realtime-mcp | Instructions file | 0 | 2mo ago | MIT | A | 2,847 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |