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/joungminsung/opendocuments/agents-mdgit clone --depth 1 https://github.com/joungminsung/OpenDocumentsWrote 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/joungminsung/opendocuments/agents-md)<a href="https://agentmods.dev/instructions/joungminsung/opendocuments/agents-md"><img src="https://agentmods.dev/badge/instructions/joungminsung/opendocuments/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 | $0.03109 | $0.03109 |
| Opus 5 | $0.01554 | $0.01554 |
| Sonnet 5 | $0.00622 | $0.00622 |
| Haiku 4.5 | $0.00311 | $0.00311 |
Grade A, and why
OpenDocuments 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 5d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
OpenDocuments는 자체 호스팅 RAG(Retrieval-Augmented Generation) 플랫폼이다. GitHub, Notion, Google Drive 등 다양한 소스의 문서를 인덱싱하고, 자연어로 질문하면 출처와 함께 답변을 제공한다.
- Repository: https://github.com/joungminsung/OpenDocuments
- License: MIT
- Node.js: >= 20.0.0
- Package Manager: [email protected]
- Build Orchestrator: Turborepo v2.3.0
- Language: TypeScript 5.5+ (strict mode, ESM)
Monorepo Structure
packages/ # 핵심 패키지 (5개)
core/ # 비즈니스 로직 전체 (RAG, ingest, storage, auth, plugin system)
server/ # HTTP API (Hono), MCP server, auth middleware, widget
cli/ # CLI 17개 명령어 (Commander.js) - npm 글로벌 패키지 'opendocuments'
web/ # React SPA (Vite + Tailwind) - private, npm 배포 안 함
client/ # TypeScript SDK (@opendocuments/client)
plugins/ # 플러그인 (21개)
model-*/ # 5개: ollama, openai, anthropic, google, grok
parser-*/ # 9개: pdf, docx, xlsx, html, jupyter, email, code, pptx
connector-*/ # 8개: github, notion, gdrive, s3, confluence, swagger, web-crawler, web-search
docs-site/ # VitePress 문서 사이트 (GitHub Pages 자동 배포)
Common Commands
npm run setup # install + build (처음 클론 시)
npm run build # turbo build (전체)
npm run test # turbo test (51 tasks, ~648 tests)
npm run dev # watch mode (전체)
npm run typecheck # turbo typecheck
# 특정 패키지만
npx turbo build --filter=opendocuments-core
npx turbo test --filter=opendocuments-core
Code Conventions
TypeScript
- strict mode 필수 (
tsconfig.base.json) - ESM: 모든 import에
.js확장자 필수import { sha256 } from './utils/hash.js' // O import { sha256 } from './utils/hash' // X any사용 금지 (web UI 제외).unknown또는 명시적 타입 사용- 공개 API에는 JSDoc 작성
Naming
| 대상 | 규칙 | 예시 |
|---|---|---|
| 파일 | kebab-case | document-store.ts |
| 클래스 | PascalCase | DocumentStore |
| 함수/변수 | camelCase | getDocumentBySourcePath |
| 상수 | UPPER_SNAKE_CASE | MAX_ALERTS |
| DB 컬럼 | snake_case | workspace_id |
| 환경변수 | UPPER_SNAKE_CASE | OPENDOCUMENTS_DATA_DIR |
| CLI 명령어 | kebab-case | auth create-key |
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.
- 5d ago First seen · 322 lines · 3,109 tokens per session scan A fab9356f644e
OpenDocuments AGENTS.md is an instructions file published in the GitHub repository joungminsung/OpenDocuments (110 stars, last pushed 1mo ago), licensed MIT. It adds 3,109 tokens to every session, about $0.0155 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
llm-wiki-agent AGENTS.md
AGENTS.md instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
personal-notes-assistant CLAUDE.md
Instructions for coeusyk/personal-notes-assistant, covering personal-notes-assistant, architecture, adding a tool, milvus notes (non-obvious, bit people twice already) and running / testing locally.
open-knowledge-format-starter AGENTS.md
Instructions for supachai-j/open-knowledge-format-starter, covering agents.md — okf bundle schema & agent operating rules, 1. directory layout (3-layer architecture), 2. concept files & frontmatter schema, 3. linking (the knowledge graph) and 4. reserved files (must follow defined structure).
llm-wiki-compiler copilot-instructions.md
Instructions for vbarsoum1/llm-wiki-compiler, covering klore — llm knowledge compiler, available commands, when to use and prerequisites.
OpenKB CLAUDE.md
Claude Code instructions for VectifyAI/OpenKB, a project described as: OpenKB: Open LLM Knowledge Base.