Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/rubatoyd/kci_openapi/claude-mdgit clone --depth 1 https://github.com/rubatoyd/KCI_openAPIWrote 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/rubatoyd/kci_openapi/claude-md)<a href="https://agentmods.dev/instructions/rubatoyd/kci_openapi/claude-md"><img src="https://agentmods.dev/badge/instructions/rubatoyd/kci_openapi/claude-md.svg" alt="Measured on agentmods" 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 | $0.09719 | $0.09719 |
| Opus 5 | $0.04859 | $0.04859 |
| Sonnet 5 | $0.01944 | $0.01944 |
| Haiku 4.5 | $0.00972 | $0.00972 |
Grade A, and why
KCI_openAPI CLAUDE.md scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- ⚠️ **KCI 방화벽은 User-Agent 필터** — `curl` 기본 UA 는 HTTP 400 "차단" 안내페이지 반환(해외 IP 문구이나 How it starts
The opening of the file, as written. The whole thing — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kci-openapi-mcp — 프로젝트 지침
한국연구재단(NRF) KCI(Korea Citation Index) 문헌·인용지수 검색·수집기. 공개 MCP 서버 + CLI. 자매 프로젝트 scienceON-mcp(
../scienceon)와 동일 아키텍처. KCI는 두 가지 공개 인터페이스를 제공하며 본 프로젝트는 둘 다 다룬다:
- REST Open API(키워드 검색형, 인증키 필요) → docs/KCI_API_GUIDE.md
- OAI-PMH(대량 수확형, 인증키 불필요) → docs/KCI_OAI_PMH_GUIDE.md
1. 목표
연구 초반 자료수집 단계에서 반복 재사용하는 도구. KCI에서 논문 서지·초록·참고문헌·저널 인용지수를 검색·수집해 후속 텍스트마이닝/계량서지 입력 데이터를 안정적으로 생산한다. ScienceON(KISTI)과 상호보완: 수록 범위 교차검증, 국문 초록 백필, KCI 연구분야 분류·인용지수 확보.
2. 확정/계획 결정사항
| 항목 | 결정 |
|---|---|
| 언어/런타임 | Python 3.10+ |
| 패키지 관리 | uv (pyproject + uv.lock). venv는 클라우드 폴더 밖 C:/Users/user/.venvs/kci-openapi-mcp (UV_PROJECT_ENVIRONMENT) |
| 의존성(계획) | mcp(FastMCP), requests, openpyxl, python-dotenv, pyyaml (pycryptodome 불필요 — KCI는 토큰/AES 없음) |
| 인터페이스 | 공용 코어 + MCP 서버(server.py) + CLI(cli.py) |
| 인터페이스(소스) | REST(openApiSearch.kci, 키 필요) + OAI-PMH(/oai/request, 무인증) — 둘 다 지원 |
| 수집 대상 | 논문(articleSearch/Detail) 우선 → 참고문헌(referenceSearch) → 저널 인용지수(citation/Detail) → OAI-PMH 대량수확 |
| 출력 | xlsx · csv · json · sqlite |
| 공개 | MIT 예정. .env·reference/·output/는 gitignore |
3. 구조 (scienceON-mcp 미러, 계획)
src/kci_mcp/
config.py # .env 로딩, Base URL/엔드포인트(REST + OAI)
client.py # REST GET / 페이징(page,displayCount≤100) / 재시도·throttle / 에러매핑
oai_client.py # OAI-PMH GET(verb) / resumptionToken 루프 / 무인증
parser.py # XML 정규화 — REST(MetaData/outputData/record) + OAI(oai_dc/oai_kci), raw 보존
models.py # Article / Reference / JournalCitation 스키마(REST·OAI 공통)
exporters.py # xlsx/csv/json/sqlite (scienceON 재사용 가능)
server.py # MCP 도구 (아래 §5)
cli.py # status/search/detail/references/citation/harvest/collect
docs/
KCI_API_GUIDE.md # ★ REST API 명세 (PDF 복구본)
KCI_OAI_PMH_GUIDE.md # ★ OAI-PMH 명세 (PDF 복구본)
reference/
KCI Open API Service 활용가이드.pdf # 공식 원본 REST (gitignore, 비공개)
KCI OAI-PMH 활용가이드.pdf # 공식 원본 OAI-PMH (gitignore, 비공개)
config/ # 검색 설정 템플릿 (search.example.yaml)
※ 현재 폴더에는 docs/(가이드 2종) + reference/(PDF 2종)만 마이그레이션 완료. src/·config/·pyproject·mcpb는 개발 단계에서 생성.
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.
- 3d ago First seen · 332 lines · 9,719 tokens per session scan A 6746e2ca525f
KCI_openAPI CLAUDE.md is an instructions file published in the GitHub repository rubatoyd/KCI_openAPI (2 stars, last pushed 3d ago), licensed MIT. It adds 9,719 tokens to every session, about $0.0486 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.