agentmods.dev

public-data-lens: Instructions file for Claude Code

CLAUDE.md

public-data-lens CLAUDE.md is an instructions file for Claude Code from hike-lab/public-data-lens. It costs 1,694 tokens per session, scanned A, original, MIT.

Project instructions for Public Data Lens, an application that normalizes public-data catalogues into a standard format and helps people search and judge the data. They describe the project structure, design documents, and rules for keeping decisions in the server and presentation in the web interface.

In plain words
What is it for?
Use them when working on the Public Data Lens server, web interface, gateway, documentation, data schemas, or user-interface implementation.
Why use it?
They give coding agents the project rules they must check before changing the application, helping prevent inconsistent calculations, altered server values, and accidental commits of generated data.

Instructions file for Claude Code

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

This is hike-lab/public-data-lens's own configuration. It tells Claude Code how to work on public-data-lens 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 public-data-lens configures →

not rated 85repo +3 13d ago A scan 1,694 tokens original MIT
View source ↗ hike-lab/public-data-lens service.datahub.kr
Reuse

Borrowing it

Nothing to install: this file belongs to hike-lab/public-data-lens. 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/hike-lab/public-data-lens/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hike-lab/public-data-lens

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 public-data-lens CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hike-lab/public-data-lens/claude-md.svg)](https://agentmods.dev/instructions/hike-lab/public-data-lens/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hike-lab/public-data-lens/claude-md"><img src="https://agentmods.dev/badge/instructions/hike-lab/public-data-lens/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,694 This file is loaded in full into every session.
When invoked 1,694 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 $0.01694 $0.01694
Opus 5 $0.00847 $0.00847
Sonnet 5 $0.00339 $0.00339
Haiku 4.5 $0.00169 $0.00169

Measured 8d ago against content hash 0cc8a127b94c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

public-data-lens 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 8d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

공공데이터 렌즈(Public Data Lens) — 중앙대학교 HIKE 연구실. 공공데이터포털 월간 목록을 정본 JSON-LD로 정규화하고 버전 관리되는 판정 규칙으로 탐색·판단 계층을 제공한다. AIRD(AI-Ready Data) 표준안의 독립적 선행 구현(의존 방향은 렌즈 → 표준).

공개 저장소다 — 커밋·문서는 공개를 전제로 쓴다. 원본 CSV·카탈로그 산출물·관측 DB는 커밋하지 않는다(data/는 gitignore, 파이프라인으로 재생성).

구조

apps/server    FastAPI. REST(/api/*) + MCP + 정본 URI 디레퍼런싱. 판정 로직 전부
apps/web       React 18 + Vite. 표현 계층만
apps/gateway   nginx real-ip
docs/          설계서·부속명세·매핑표·배포·호환성·개인정보 고지

설계 문서 (작업 전 확인)

문서 내용
DESIGN.md 웹 표면의 제품 설계 원칙
docs/UI_IMPLEMENTATION_GUIDE.md 필드 매핑·컴포넌트 계약·Phase·DoD
docs/부속명세_v1.0.md Tool별 JSON Schema + 공통 계약
apps/server/datanav/spec/tool-schemas-v1.7.0.json enum·필드의 정본

UI 작업 시 DESIGN.md와 docs/UI_IMPLEMENTATION_GUIDE.md를 먼저 읽는다. 문서와 계약이 어긋나면 계약이 이긴다.

책임 분리 (설계서 §2)

재현되어야 하는 판정은 서버가 결정론적으로 수행한다. 목적 의존적 해석은 호스트 LLM이 한다. 프론트엔드는 표현만 한다.

불변식

  1. 프론트엔드에 새로운 점수를 만들지 않는다 — readiness, quality, suitability, 종합 적합도. 계약은 kdp:qualityTier·kdp:diagnosticMaturity를 null 고정으로 명시한다.
  2. 판정 임계값을 프론트엔드에서 정하지 않는다 — topPercent <= 10 같은 컷오프.
  3. 서버가 준 값을 변형하지 않는다 — region.name을 정규식으로 자르는 등.
  4. 서버 경고 문안을 치환하지 않는다 — warnings[] 원문을 툴팁으로 밀어내지 않는다.
  5. 문자열 패턴으로 계약 의미를 추론하지 않는다 — ranking.method.includes('bm25') 등.
  6. 백엔드 로직을 프론트엔드에서 재구현하지 않는다 — 질의→필터 해석은 서버 plan-assembly-v1.0(apps/server/datanav/api/plan.py)에 이미 있다.
  7. 모든 데이터 호출은 apps/web/src/api.js를 경유한다. raw fetch 금지 — 익명 로그 옵트아웃(DNT/GPC)과 오류 모델 언랩이 여기에 있다.
  8. api.js의 기존 메서드 시그니처를 바꾸지 않는다. 메서드 추가는 허용.

계약 의미 — 위반하면 제품이 거짓말을 한다

NOT_COLLECTED / QUEUED / COLLECTING        수집 상태다. 품질 문제가 아니다
MISSING_FROM_SNAPSHOT                      관찰 사실이다. 폐기 확정이 아니다
                                           (폐기는 OFFICIALLY_WITHDRAWN만)
UNKNOWN (freshness)                        판단 불가다. 나쁨이 아니다
INFERRED_* (region)                        추론이다. 틀렸다는 뜻이 아니다
WITHHELD_BY_LICENSE / _SAFETY              정책적 보류다
검색 결과 없음                              데이터 부재가 아니다
search_by_columns 결과 없음                 컬럼 부재가 아니다 (미수집일 수 있음)
familyCandidate (UNREVIEWED)               자동 후보다. 확정된 계열이 아니다
LEGITIMATE_SPLIT                           정당한 분리다. 파편화가 아니다
계열 후보 존재                              문제 신호가 아니다
family 축 available=false                  미산출이다. 0건이 아니다

Read the full file on GitHub · 116 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. 8d ago First seen · 116 lines · 1,694 tokens per session scan A 0cc8a127b94c

Subscribe to this mod's changes

public-data-lens CLAUDE.md is an instructions file published in the GitHub repository hike-lab/public-data-lens (85 stars, last pushed 13d ago), licensed MIT. It adds 1,694 tokens to every session, about $0.0085 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 2026-08-30.

ai-agentsai-ready-datadata-catalogdata-discoverydata-qualitydcat
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

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 · 7,104 tokens