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/daangn/seed-design/agents-mdgit clone --depth 1 https://github.com/daangn/seed-designWrote 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/daangn/seed-design/agents-md)<a href="https://agentmods.dev/instructions/daangn/seed-design/agents-md"><img src="https://agentmods.dev/badge/instructions/daangn/seed-design/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 | $0.00786 | $0.00786 |
| Opus 5 | $0.00393 | $0.00393 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
seed-design 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 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.
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
AGENTS.md
AI 어시스턴트가 이 저장소에서 작업할 때 참고하는 가이드.
프로젝트 개요
SEED Design은 당근의 디자인 시스템이다. 기술적 상세는 @TECH.md 참고.
AGENTS.md 역할
각 폴더의 AGENTS.md는 해당 폴더의 개요와 컨벤션을 설명한다. 기술 상세는 TECH.md에, 사용자 대상 설명은 README.md에 작성한다.
필수 3섹션
- 디렉토리 개요: 폴더의 역할을 1-2문장으로 설명하고 상/하위 연결만 간단히 언급한다.
- 파일 작성 컨벤션: 파일/디렉토리 네이밍 규칙과 barrel file 사용 원칙을 적는다.
- 코드 작성 컨벤션: 해당 폴더에 적용되는 패턴과 import/export 규칙을 정리한다.
계층 원칙
- 상위 AGENTS는 얕고 넓게: 폴더군의 역할과 연결 흐름만
- 하위 AGENTS는 깊고 좁게: 해당 폴더에 국한된 구조와 컨벤션
- 중복 없이 계층적으로 작성
AGENTS.md가 필요한 디렉토리
핵심 도메인/패키지 폴더에는 AGENTS.md를 두고, 생성물/의존성 폴더(node_modules, dist 등)에는 두지 않는다.
문서 역할 분리
| 문서 | 역할 | 대상 |
|---|---|---|
AGENTS.md |
폴더 개요 + 컨벤션 | AI 에이전트 |
TECH.md |
기술 상세, 아키텍처, 명령어 | AI 에이전트 |
README.md |
패키지 소개, 사용법, 개발 방법 | 사람 |
각 패키지/폴더별 세부 규칙은 해당 디렉토리의 AGENTS.md에 명시되어 있으며, 해당 경로에서 작업할 때만 읽힌다.
Boundaries
-
✅ Always:
bun generate:all실행 후 변경사항 확인- 패키지 수정 직후 해당 경로 테스트만 실행 (경로별 명령어는 @TECH.md의 「테스트」 표)
- 테스트 실행 후 커밋 (
bun test:all)
-
⚠️ Ask first:
- 새 패키지 추가
- tsconfig/biome.json 설정 변경
- CI 워크플로우 수정
- 외부 의존성 추가
-
🚫 Never:
packages/css/vars/,packages/css/recipes/직접 수정packages/qvism-preset/src/vars/직접 수정.env, API 키, 시크릿 커밋npm/pnpm/yarn사용 (bun전용)dist/,node_modules/수정
Git 규칙
- 커밋 메시지는 반드시 영어로 작성한다. Conventional Commits 형식을 따른다:
type(scope): subject- 예:
feat(button): add loading state,fix(tooltip): correct z-index,docs: update component rules
- 예:
- PR 제목도 반드시 영어로 작성한다. 커밋 메시지와 동일한 Conventional Commits 형식을 따른다.
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 · 69 lines · 786 tokens per session scan A 2c4a4860d1ec
seed-design AGENTS.md is an instructions file published in the GitHub repository daangn/seed-design (1,074 stars, last pushed 3d ago), licensed Apache-2.0. It adds 786 tokens to every session, about $0.0039 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 2026-08-31.
Other instructions, from other repositories
daisyui code_generation_with_git.instructions.md
Instructions for saadeghi/daisyui, covering activation, initial setup, development loop, error handling and session end.
starwind-ui AGENTS.md
Instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
wonder-blocks CLAUDE.md
Claude Code instructions for Khan/wonder-blocks, covering wonder blocks design system, technology stack, coding conventions, file & export naming and typescript.
wonder-blocks storybook.instructions.md
Storybook best practices for Wonder Blocks component stories.
wonder-blocks AGENTS.md
AGENTS.md instructions for Khan/wonder-blocks, covering wonder blocks – agentic workflows & storybook mcp, installing the mcp (consumer setup), storybook mcp server, when it’s available and mcp endpoint.
openbridge-webcomponents watch-radial-instruments.instructions.md
Instructions for Ocean-Industries-Concept-Lab/openbridge-webcomponents, covering watch & radial instruments, architecture overview, key principle: logic in watch.ts, instruments stay thin, shared sibling modules and layering & stacking pattern.