Borrowing it
Nothing to install: this file belongs to gguloadoong/idea-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gguloadoong/idea-factory/main/CLAUDE.mdgit clone --depth 1 https://github.com/gguloadoong/idea-factoryWrote 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/gguloadoong/idea-factory/claude-md)<a href="https://agentmods.dev/instructions/gguloadoong/idea-factory/claude-md"><img src="https://agentmods.dev/badge/instructions/gguloadoong/idea-factory/claude-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 | $0.00891 | $0.00891 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
idea-factory CLAUDE.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 8d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
idea-factory — 메타 레포 거버넌스
이 레포는 Claude Code + OMC 기반 가상 스타트업 팩토리의 템플릿·스킬·스크립트 원본이다.
여기서 작업하면 /start-company로 생성되는 모든 다운스트림 레포에 영향이 전파된다.
다운스트림 프로젝트에서 쓰이는 CLAUDE.md는 이 파일이 아니라 templates/CLAUDE.md.tmpl에서 나온다.
작업 영역 구분
| 디렉터리 | 역할 | 변경 빈도 |
|---|---|---|
templates/ |
다운스트림에 복사되는 파일 원본 (hooks, agents, scripts 등) | 높음 — 변경 시 전파 주의 |
skills/ |
/start-company 실행 로직 (SKILL.md, HARNESS-GUIDE.md) |
중간 |
scripts/ |
메타 레포 관리 스크립트 (sync-downstream.sh 등) |
낮음 |
docs/ |
한국어 가이드 등 문서 | 낮음 |
보호 영역 — 반드시 PR 경유
다음 파일은 직접 main 커밋 금지. Issue → Branch → PR → 리뷰 후 머지:
sync-manifest.json— managed 항목 변경 시sync-downstream.sh재실행 필요downstream-registry.json— 10개 다운스트림 레포 추적 목록templates/CLAUDE.md.tmpl— 생성되는 모든 프로젝트의 헌법 (80줄 제한 유지)templates/settings.json—permissions.deny및defaultMode포함 (자율 루프 호환성 임계값)templates/hooks/— PreToolUse 훅은 반드시 exit-0 로깅 전용 (blocking 금지)
전파 영향 경고
templates/ 하위 파일을 변경하면 현재 downstream-registry.json에 등록된
10개 레포 (signalplay, chimp-pick, market-dashboard-v5, trading-signal-bot,
bull-vs-bear, costock, reel-forge, aptner, catchflow, market-dashboard-v2)
에 영향을 줄 수 있다.
변경 후 sync-manifest.json의 managed 항목에 해당하는 경우 반드시 갱신하고
sync-downstream.sh로 전파 여부를 확인한다.
커밋 규약
| 타입 | 경로 | 방식 |
|---|---|---|
feat: fix: |
신규 기능·버그 수정 | Issue → feature/#N-설명 브랜치 → PR |
refactor: docs: chore: |
리팩터·문서·유지보수 | main 직접 커밋 허용 |
한국어 원자적 커밋. 예: feat: VALIDATE 게이트 4번째 리뷰어 추가 (#12)
모델 라우팅
- Sonnet 4.6: 기본 작업 전반 (템플릿 편집, 스크립트 수정, 문서 작업)
- Opus 4.7: 아키텍처 결정, 보안 리뷰,
HARNESS-GUIDE.md수정, 다운스트림 영향 분석
시크릿 규칙
.env파일 복사 또는 커밋 절대 금지cat .env금지 → 키 존재 확인은grep -c "KEY_NAME" .env만 사용- 터미널·대화창에 API 키값 노출 금지
참조
- AGENTS.md — OMC 진입점 및 에이전트 목록
- ARCHITECTURE.md — 시스템 아키텍처 전체 구조
- skills/start-company/HARNESS-GUIDE.md — 설계 결정 상세 근거
- CHANGELOG.md — 버전별 변경 이력
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.
- 8d ago First seen · 76 lines · 891 tokens per session scan A 6e4e222aa1a7
idea-factory CLAUDE.md is an instructions file published in the GitHub repository gguloadoong/idea-factory (2 stars, last pushed 4mo ago), licensed MIT. It adds 891 tokens to every session, about $0.0045 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.