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/hletrd/kiwi-paper/agents-mdgit clone --depth 1 https://github.com/hletrd/kiwi-paperWrote 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/hletrd/kiwi-paper/agents-md)<a href="https://agentmods.dev/instructions/hletrd/kiwi-paper/agents-md"><img src="https://agentmods.dev/badge/instructions/hletrd/kiwi-paper/agents-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 | $0.01631 | $0.01631 |
| Opus 5 | $0.00816 | $0.00816 |
| Sonnet 5 | $0.00326 | $0.00326 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
kiwi-paper AGENTS.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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — kiwi-paper
이 문서는 AI 코딩 에이전트(Claude Code, OpenCode, Codex 등)가 이 프로젝트에서 작업할 때 참고하는 가이드입니다.
프로젝트 개요
kiwi-paper는 학술 논문 PDF나 전공 서적을 나무위키 스타일의 마크다운 문서로 변환하는 Claude Code 스킬입니다.
- 스킬 정의:
SKILL.md(프로젝트 루트 및~/.claude/skills/kiwi-paper/) - 예제 출력:
examples/디렉토리 - 설치 스크립트:
install.sh
핵심 컨셉
나무위키 스타일이란?
나무위키는 한국의 대표적인 위키 플랫폼으로, 다음과 같은 독특한 문체를 가집니다:
취소선: 유머를 전달하는 핵심 장치. 진짜 내용 옆에 농담을 취소선으로 표시- 여담 섹션: 본문 끝에 관련 트리비아, 뒷이야기를 모아두는 섹션
- 각주 유머: 각주에 출처뿐 아니라 드립을 숨겨두는 문화
- 구어체 톤: 백과사전과 달리 편하고 재미있는 말투
- 괄호 코멘터리: (이런 식으로 중간에 편집자 의견을 삽입)
4단계 파이프라인
- 초안 작성 (Draft): PDF 내용을 나무위키 스타일로 변환
- 다듬기 (Refine): 구조, 유머 밸런스, 링크를 보강
- 휴머나이즈 (Humanize): AI가 쓴 티를 제거하고 자연스러운 한국어로 다듬기
- HTML 렌더링 (Render): 마크다운을 나무위키 스타일 HTML로 변환
디렉토리 구조
kiwi-paper/
├── AGENTS.md # 이 파일 — AI 에이전트 가이드
├── SKILL.md # 스킬 정의 (핵심 파일)
├── README.md # 프로젝트 소개
├── LICENSE # MIT 라이선스
├── install.sh # 스킬 + 렌더러 설치 스크립트
├── .gitignore
├── examples/
│ └── attention-is-all-you-need.md # 예제 출력
└── renderer/ # Markdown → HTML 렌더러
├── package.json # ESM 패키지 (Node.js >= 20)
└── src/
├── render.mjs # CLI 엔트리 포인트
└── template.mjs # HTML 템플릿 (CSS/JS 인라인)
에이전트별 작업 가이드
렌더러 작업 시
renderer/디렉토리는 독립 Node.js 패키지 (ESM,"type": "module")- 엔트리 포인트:
renderer/src/render.mjs— CLI (-i,-o필수 옵션) - 템플릿:
renderer/src/template.mjs—renderPage(),renderIndexPage()export - 의존성 변경 시
cd renderer && npm install필요 - 테스트:
node renderer/src/render.mjs -i examples/ -o dist/
CLI 인터페이스:
node render.mjs -i <path|url...> -o <dir> [--title <str>] [--no-toc] [--single]
파이프라인: marked (GFM) → footnotes → KaTeX (서버사이드) → Shiki (듀얼 테마) → heading IDs → .md→.html 링크 변환
스킬 수정/개선 시
SKILL.md를 읽고 현재 스킬 정의를 파악- 수정이 필요한 부분을 변경
- 반드시 프로젝트 루트의
SKILL.md와~/.claude/skills/kiwi-paper/SKILL.md양쪽을 동기화 examples/디렉토리의 예제가 변경된 스킬과 일관성 있는지 확인
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.
- 4d ago First seen · 125 lines · 1,631 tokens per session scan A fce2875f7dd9
kiwi-paper AGENTS.md is an instructions file published in the GitHub repository hletrd/kiwi-paper (15 stars, last pushed 5mo ago), licensed MIT. It adds 1,631 tokens to every session, about $0.0082 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.
Other instructions, from other repositories
mcp-pandoc AGENTS.md
Instructions for vivekVells/mcp-pandoc, covering agents.md, what this is, where things are, deeper context and commands.
agentic-resume-builder CLAUDE.md
Claude Code instructions for WtotdeD/agentic-resume-builder, covering agentic-resume-builder development guidelines, what this repo is, active technologies, package manager and validation.
fcp-sheets CLAUDE.md
Instructions for os-tack/fcp-sheets, covering fcp-sheets, project overview, architecture, key patterns and commands.
omg-payment-skill GEMINI.md
Gemini CLI instructions for chenmitchell/omg-payment-skill, covering google gemini 使用指引, 適用版本, 載入方式, gemini web / app and gemini cli.
paperless-ngx-mcp-server CLAUDE.md
Claude Code instructions for cbsmiley/paperless-ngx-mcp-server, covering claude.md, project overview, common commands, architecture and entry points.
hermes-procurement-pricing-mcp AGENTS.md
AGENTS.md instructions for felix-windsor/hermes-procurement-pricing-mcp, a project described as: Secure procurement quotation comparison MCP service with document parsing, mock market pricing, anomaly detection, and Telegram/Hermes integration.