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/gemini-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/gemini-md)<a href="https://agentmods.dev/instructions/hletrd/kiwi-paper/gemini-md"><img src="https://agentmods.dev/badge/instructions/hletrd/kiwi-paper/gemini-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 5.1 | $0.00421 | $0.00421 |
| Opus 5 | $0.00211 | $0.00211 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
kiwi-paper GEMINI.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 6d 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.
What it actually says
kiwi-paper — Gemini CLI Instructions
이 저장소는 모든 종류의 기술 문서를 나무위키 스타일로 변환하는 도구입니다.
사용법
사용자가 kiwi-paper 변환을 요청하면 SKILL.md 파일의 지시사항을 따르세요.
핵심 지시사항은 SKILL.md에 있습니다. 반드시 읽고 4단계 파이프라인을 따르세요.
4단계 파이프라인
- 초안 작성 — 입력 문서를 나무위키 스타일 마크다운으로 변환
- 다듬기 — 구조, 유머, 링크, 이미지 보강
- 휴머나이즈 — AI 티 제거, 자연스러운 한국어
- HTML 렌더링 —
node renderer/src/render.mjs -i <file> -o <dir>
지원 문서 유형 (12종)
학술 논문, 전공 서적, 기술 명세서/RFC, API 문서, 사용설명서, 뉴스/기사, 블로그, 법률 문서/약관, 특허, 백서, 릴리스 노트, 강의 노트
핵심 규칙
- 취소선(~~) 섹션당 3-5개, 전체 15개 이상
- 각주 8개 이상 (출처 6 : 유머 4 비율)
- 여담 섹션 5개 항목 이상
- 이미지: 원본의 모든 Figure/Table 포함, 없으면 WebSearch로 찾기
--split옵션으로 섹션별 분할 가능
파일 구조
SKILL.md— 핵심 변환 규칙 (반드시 읽을 것)AGENTS.md— 에이전트 가이드renderer/— HTML 렌더러 (Node.js >= 20)examples/— 변환 예제
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.
- 6d ago First seen · 36 lines · 421 tokens per session scan A 2144d9ee03c1
kiwi-paper GEMINI.md is an instructions file published in the GitHub repository hletrd/kiwi-paper (15 stars, last pushed 5mo ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 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
translate-book CLAUDE.md
Instructions for deusyu/translate-book, covering claude.md, project, structure, testing changes and then run translation via the skill.
adeu AGENTS.md
AGENTS.md instructions for dealfluence/adeu, covering adeu agent instructions, repository structure & packages, commands & verification workflow, python (python/) and node.js (node/).
mcp-arabic-ms-word AGENTS.md
AGENTS.md instructions for MarwanDevSpace/mcp-arabic-ms-word, covering 3. web image research & assets/ directory sourcing engine, 4. universal arabic typography & bidi openxml standards, 5. clean workspace protocol (zero pollution) and 6. master skills reference.
translate-book CLAUDE.md
Instructions for trananhtung/translate-book, covering claude.md, project, structure, testing changes and then run translation via the skill.
pdf2zh-next-mcp CLAUDE.md
Claude Code instructions for JaeHyeon-KAIST/pdf2zh-next-mcp, covering pdf2zh-next-mcp, 아키텍처, 파일 구조, 주요 설계 결정 and 바이너리 탐색.
awesome-epub-translator-skill CLAUDE.md
Claude Code instructions for ludengz/awesome-epub-translator-skill, covering claude.md, project overview, architecture, key design decisions and working on this project.