seoul-realtime-air-by-region-mcp: Instructions file for Claude Code

CLAUDE.md

seoul-realtime-air-by-region-mcp CLAUDE.md is an instructions file for Claude Code from hlucent/seoul-realtime-air-by-region-mcp. It costs 2,097 tokens per session, scanned A, original, MIT.

Repository instructions for agents working on a Seoul air-quality service. They specify the required reading order, implementation constraints, response parsing, testing duties, and deployment limits.

In plain words
What is it for?
They are for implementing and locally testing the service, handling JSON and XML responses, configuring its HTTP server, maintaining the .env file, and preparing—but not performing—Fly.io deployment.
Why use it?
They reduce unsafe or inconsistent changes by defining what to check first, how to handle API responses, and which deployment commands agents must not run.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is hlucent/seoul-realtime-air-by-region-mcp's own configuration. It tells Claude Code how to work on seoul-realtime-air-by-region-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything seoul-realtime-air-by-region-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hlucent/seoul-realtime-air-by-region-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.

Copy the file
curl -O https://raw.githubusercontent.com/hlucent/seoul-realtime-air-by-region-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hlucent/seoul-realtime-air-by-region-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for seoul-realtime-air-by-region-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hlucent/seoul-realtime-air-by-region-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hlucent/seoul-realtime-air-by-region-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hlucent/seoul-realtime-air-by-region-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/seoul-realtime-air-by-region-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.

agentmods 80×15 button for seoul-realtime-air-by-region-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hlucent/seoul-realtime-air-by-region-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/seoul-realtime-air-by-region-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,097 This file is loaded in full into every session.
When invoked 2,097 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02097 $0.02097
Opus 5 $0.01048 $0.01048
Sonnet 5 $0.00419 $0.00419
Haiku 4.5 $0.00210 $0.00210

Measured 11d ago against content hash db724c343b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

seoul-realtime-air-by-region-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 11d 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.

CLAUDE.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — seoul-realtime-air-by-region-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 logs 등 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 "PowerShell 창에서 fly launch --no-deploy부터 진행하세요"라고 안내한다.

기술적으로 반드시 적용할 것

.env

BOM 없는 UTF-8로 저장. python-dotenv가 BOM 있는 파일에서 키를 못 읽는 문제 재발 방지.

server.pymcp.run()

mcp.run(transport="streamable-http", host="0.0.0.0", port=port, stateless_http=True)

stateless_http=True 절대 누락 금지 — 없으면 fly.io 멀티머신 환경에서 세션 404, 커넥터에 "사용 가능한 도구 없음"으로 표시되는 문제가 재발한다.

응답 파싱: JSON 우선, XML 폴백 필수

정상 응답은 JSON이어도, 일부 에러 응답(INFO-100, INFO-200 등)이 TYPE=json 요청에도 XML로 돌아올 수 있다. response.json()이 실패하면 정규식으로 <CODE>/<MESSAGE> 패턴을 추출하는 폴백 파서를 반드시 구현한다.

import re

def parse_response(text: str) -> dict:
    try:
        return json.loads(text)
    except ValueError:
        code_match = re.search(r"<CODE>(.*?)</CODE>", text)
        msg_match = re.search(r"<MESSAGE>(.*?)</MESSAGE>", text)
        return {
            "RESULT": {
                "CODE": code_match.group(1) if code_match else "UNKNOWN",
                "MESSAGE": msg_match.group(1) if msg_match else text[:200],
            }
        }

API 키 취급 원칙

  • 실제 키 값은 os.environ으로만 읽는다. 하드코딩 금지.
  • .env 갱신 후 재테스트 전, 파일 크기/앞부분 문자열을 이전 값과 비교해 실제로 바뀌었는지 확인한다.
  • 디버깅 시 키를 표준출력에 그대로 찍지 않는다. 필요하면 앞 4자리 + ... + 길이만 출력.
  • 키는 쿼리 파라미터가 아니라 URL 경로 세그먼트일 가능성이 높다 (DEVPLAN.md 1-1절 참고). 실측 단계에서 경로 삽입 방식(/{KEY}/json/RealtimeCityAir/...)을 우선 시도하고, ERROR-300이 반복되면 다른 방식도 시도한다.

작업 순서

  1. requirements.txt (fastmcp, httpx, python-dotenv)
  2. seoul_api.py — API 호출 + 에러코드 매핑 (JSON 우선, XML 폴백 포함), 경로 세그먼트 방식 URL 빌더
  3. server.py — 툴 2개 정의(docstring에 필드/단위 명시), stateless_http=True 필수, 아래 "rate limit 미들웨어" 포함
  4. .env.example, .gitignore
  5. 로컬 테스트 (실제 키로 각 툴 호출):
    • URL 구조(키의 위치: 쿼리 vs 경로)부터 확인. ERROR-300 반복 시 키 위치 의심.
    • SAREA_NM/MSRSTN_NM 조합별 실측: 둘 다 생략, SAREA_NM만, 둘 다 지정, MSRSTN_NM만 (권역 생략) — 각각 정상 동작하는지 확인 후 DEVPLAN.md 2절 "실측 필요 항목" 결과를 DEVLOG.md에 기록
    • START_INDEX/END_INDEX 범위를 넓혀 실제 여러 건이 반환되는지 확인
  6. FastMCP 서버 스모크 테스트 (initialize 요청까지만)
  7. Dockerfile, fly.toml아래 "표준 fly.toml 템플릿" 그대로 사용, fly launch의 자동 생성을 기다리지 않는다.
  8. README/DEVLOG 갱신 — 실측으로 확인된 제약사항을 실제 동작 기준으로 정확히 기술
  9. git add/commit/push까지 수행 (push는 자동 진행 가능 — 백업 목적, 실제 배포와 무관)
  10. 여기서 정지 — 사용자에게 PowerShell에서 fly launch --no-deploy부터 진행하도록 안내

Read the full file on GitHub · 145 lines

Changes

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.

  1. 11d ago First seen · 145 lines · 2,097 tokens per session scan A db724c343b27

Subscribe to this mod's changes

seoul-realtime-air-by-region-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/seoul-realtime-air-by-region-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 2,097 tokens to every session, about $0.0105 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens