seoul-air-quality-mcp: Instructions file for Claude Code

CLAUDE.md

seoul-air-quality-mcp CLAUDE.md is an instructions file for Claude Code from hlucent/seoul-air-quality-mcp. It costs 2,275 tokens per session, scanned A, original, MIT.

A set of project instructions for extending a Seoul air-quality MCP service, which provides air-quality information for Seoul. It defines required implementation steps, testing rules, and deployment limits.

In plain words
What is it for?
Use it when modifying that service, especially when working on district-level air-quality data, tests, documentation, or deployment preparation.
Why use it?
It keeps changes aligned with the existing project and records how to handle known data and naming problems.

Instructions file for Claude Code

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

This is hlucent/seoul-air-quality-mcp's own configuration. It tells Claude Code how to work on seoul-air-quality-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-air-quality-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hlucent/seoul-air-quality-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-air-quality-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hlucent/seoul-air-quality-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-air-quality-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hlucent/seoul-air-quality-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/seoul-air-quality-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,275 This file is loaded in full into every session.
When invoked 2,275 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 $0.02275 $0.02275
Opus 5 $0.01137 $0.01137
Sonnet 5 $0.00455 $0.00455
Haiku 4.5 $0.00228 $0.00228

Measured 9d ago against content hash c87fcddd61a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

seoul-air-quality-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 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.

CLAUDE.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — 서울시 대기환경정보 MCP 확장 작업 지침

1. 절대 규칙

  • DEVPLAN.md 하나만 먼저 읽고 시작. 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.
  • 이번 작업은 신규 프로젝트가 아니라 기존 seoul-air-quality-mcp 저장소에 대한 확장 작업이다. 새 폴더/새 저장소를 만들지 않는다. 반드시 기존 프로젝트 폴더 (C:\Users\hwang\Projects\seoul-air-quality-mcp) 안에서 작업한다.
  • fly launch, fly secrets set, flyctl deploy, fly logs 등 fly.io 관련 명령은 Claude Code가 절대 스스로 실행하지 않는다.
  • 배포 준비(코드 구현, 로컬 테스트, git commit/push)가 끝나면 정지하고, 사용자에게 PowerShell에서 flyctl deploy를 직접 실행하도록 안내한다.

2. 작업 순서

0단계(중요, 반드시 먼저 읽을 것): DEVPLAN.md 0-1절에 기존 코드의 버그가 기록되어 있다. 기존 get_realtime_air_quality 함수가 실제로는 RealtimeCityAir(권역별 데이터)를 호출하고 있으며, 이는 "자치구별"이라는 이름·설명과 맞지 않는다. 이번 작업은 이 버그의 개명 정정진짜 자치구별 데이터셋 신규 구현을 함께 수행한다. 아래 순서를 반드시 지킨다 (순서가 바뀌면 함수명이 충돌한다).

  1. 기존 저장소 구조를 먼저 파악한다 — main.py, API 호출 공통 함수, _DATASET_INFO류 메타데이터 딕셔너리가 있는지 확인. 특히 main.py 528행 부근의 기존 get_realtime_air_quality 함수 정의부를 정확히 찾아둔다.
  2. 개명을 먼저 수행한다: 기존 get_realtime_air_quality 함수명을 get_zonal_realtime_air_quality로 변경한다. 함수 내부의 API 호출 URL, 파싱 로직은 절대 변경하지 않는다 — 이미 RealtimeCityAir를 정상 호출하고 있으므로 그대로 둔다. docstring과 함수 설명만 "서울시 권역별 실시간 대기환경 현황"에 맞게 정정한다. 이 저장소에 도구 목록을 등록하는 곳(FastMCP 데코레이터, _DATASET_INFO 등)이 있다면 그곳의 이름도 함께 변경한다.
  3. 개명이 끝난 뒤에만 신규 6개 도구를 구현한다 (DEVPLAN.md 2-2절). 이때 get_realtime_air_quality라는 이름을 진짜 "서울시 실시간 자치구별 대기환경 현황"(ListAirQualityByDistrictService)에 새로 부여해 신규 함수로 구현한다. 2단계가 먼저 끝나 있지 않으면 이름이 겹친다.
  4. 각 함수는 기존 공통 API 호출 함수(JSON 우선, XML <CODE>/<MESSAGE> 폴백 파싱 포함)를 재사용한다. 새로 만들지 않는다.
  5. docstring에 필드명·단위·출처 표기 필수 문구를 기존 도구들과 동일한 형식으로 삽입한다.
  6. 로컬 실측 테스트 — 아래 3절 "실측 필요 항목" 순서대로 진행. 개명된 get_zonal_realtime_air_quality가 개명 전과 동일하게 정상 동작하는지 회귀 테스트를 반드시 포함한다.
  7. _DATASET_INFO(또는 동등한 메타데이터 구조)에 신규 6개 항목 등록 — 서비스명, 제공부서, 원본 URL 포함. 개명된 항목의 메타데이터도 "권역별"에 맞게 갱신.
  8. README.md의 Dataset Registry 표를 16개 → 22개로 갱신. DEVPLAN.md 1-8절의 "서울시 시간 평균 대기오염도 정보" 표기 정정(붙여쓰기 → 띄어쓰기)도 이 시점에 함께 반영한다. "배포 검증 이력" 절에 이번 버그 발견·수정 사실을 날짜와 함께 명확히 기록한다 — 과거 README에 잘못 기재된 서비스명 매핑이 어떻게 틀렸었는지, 무엇으로 바로잡았는지 남겨서 향후 재발을 막는다.
  9. DEVLOG.md에 이번 확장 작업(버그 수정 포함) 기록 추가.
  10. python3 -m py_compile 등으로 구문 검증.
  11. git add/commit/push까지 수행 (본인 소유 저장소 백업이므로 자동 진행 가능). 커밋 메시지에 이번 작업이 "기능 추가"뿐 아니라 "버그 수정"을 포함한다는 점을 명시한다 (예: fix: 잘못 명명된 get_realtime_air_quality를 get_zonal_realtime_air_quality로 정정, 진짜 자치구별 API 신규 추가).
  12. 여기서 정지 — 배포는 사용자가 PowerShell에서 직접 수행.

Read the full file on GitHub · 118 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. 9d ago First seen · 118 lines · 2,275 tokens per session scan A c87fcddd61a9

Subscribe to this mod's changes

seoul-air-quality-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/seoul-air-quality-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 2,275 tokens to every session, about $0.0114 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

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

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

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

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.

deepseek-ai/deepseek-harness · 3,735 tokens