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/leeyudok/agents-scaffold/agents-mdgit clone --depth 1 https://github.com/LeeYudok/agents-scaffoldWrote 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/leeyudok/agents-scaffold/agents-md)<a href="https://agentmods.dev/instructions/leeyudok/agents-scaffold/agents-md"><img src="https://agentmods.dev/badge/instructions/leeyudok/agents-scaffold/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 | $0.01998 | $0.01998 |
| Opus 5 | $0.00999 | $0.00999 |
| Sonnet 5 | $0.00400 | $0.00400 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
agents-scaffold 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — {{PROJECT_NAME}}
이 파일은 이 저장소에서 작업할 때 AI 에이전트(Claude Code·Gemini CLI·Codex 등)가 따르는
단일 진실원천(SSOT) 이다. 프로젝트 브레인. CLAUDE.md·GEMINI.md 는 이 파일을 참조한다.
이 파일은 자체 완결이어야 한다 — 아래 P0/P1 은 다른 파일 로딩 없이 여기서 읽힌다.
@ import 는 Claude Code 전용 문법이라 하네스 중립 파일인 여기에 두지 않는다
(메모리 인덱스 자동 로드는 CLAUDE.md·GEMINI.md 가 담당).
메모리 경로 오버라이드
이 프로젝트의 auto-memory SSOT는 .claude/memory/ 이다.
- 시스템 기본 경로(
~/.claude/projects/.../memory/)는 사용하지 않는다. - 모든 메모리 읽기/쓰기는
.claude/memory/하위에서 수행한다. MEMORY.md가 인덱스(단일), 타입접두project_/feedback_/reference_/user_.user_*.md만 개인(gitignore), 그 외는 팀 공유.
.claude/ 인프라
개요는 .claude/README.md, 각 하위 디렉터리 README 에 작성 골격과 컨벤션이 있다.
| 디렉터리 | 역할 | 상세 |
|---|---|---|
agents/ |
서브에이전트 정의 (code-reviewer, security-audit, db-migration, sdlc-*, agent-evolve) | README |
commands/ |
커스텀 슬래시 커맨드 (fix-issue, sdlc-cycle, sonar, knowledge-graph) | README |
hooks/ |
강제 게이트 — pre-commit, 자동 포맷, observe-lite, 메모리 리마인드 | README |
memory/ |
프로젝트 메모리 SSOT — MEMORY.md 인덱스 + 타입접두 파일 | README |
rules/ |
맥락 인지 룰 — paths: 스코프 조건부 로드 |
README |
skills/ |
상황별 절차 — review, status, search-first, memory-factcheck, security-precheck, docs-sync, grill-me 등 | README |
workflows/ |
저장형 Workflow 오케스트레이션 스크립트(*.js) — rules-audit 예제 |
README |
scripts/ |
레포 로컬 헬퍼 — knowledge_graph.py(문서 그래프 + 링크 체커) | README |
settings.json 에 deny 규칙과 훅 바인딩이 있다. 문서 정합성 점검·온보딩은
/knowledge-graph 실행.
프로젝트 개요
스택
명령
컨벤션
- skill/agent 신규 생성 시
{{PROJECT_NAME}}-prefix 네임스페이스 - 세부 규약은
.claude/rules/의 paths 스코프 룰 참조 - 스택별 세부 규약 → 아래 우선순위 체계 참조
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 · 115 lines · 1,998 tokens per session scan A d95761804132
agents-scaffold AGENTS.md is an instructions file published in the GitHub repository LeeYudok/agents-scaffold (25 stars, last pushed 6d ago), licensed MIT. It adds 1,998 tokens to every session, about $0.0100 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
claude-code-starter-kit CLAUDE.md
Instructions for dachivadachkoria/claude-code-starter-kit, covering project: [your project name], tech stack, project structure, development commands and install dependencies.
ai-rules CLAUDE.md
Claude Code instructions for SpaceMalamute/ai-rules, covering ai rules - multi-target ai tool configurations, structure, principles, adding a technology and git.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
sugar AGENTS.md
AGENTS.md instructions for roboticforce/sugar, covering sugar - agents.md, git branching rules (strict), always create branches from develop, after work is complete and then create pr targeting develop.
nextjs-skills CLAUDE.md
Instructions for mohamed-hossam1/nextjs-skills: All contribution rules — style, naming, file layout, verification — live in AGENTS.md. Read that first.