Borrowing it
Nothing to install: this file belongs to fivetaku/idea-lab. 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/fivetaku/idea-lab/main/.claude/commands/draft.mdgit clone --depth 1 https://github.com/fivetaku/idea-labWrote 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/commands/fivetaku/idea-lab/draft)<a href="https://agentmods.dev/commands/fivetaku/idea-lab/draft"><img src="https://agentmods.dev/badge/commands/fivetaku/idea-lab/draft/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/fivetaku/idea-lab/draft"><img src="https://agentmods.dev/badge/commands/fivetaku/idea-lab/draft.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00103 | $0.01039 |
| Opus 5.5 | $0.00041 | $0.00416 |
| Sonnet 5.5 | $0.00021 | $0.00208 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
draft 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 2mo 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
/draft
브리프를 받아 20-knowledge/·30-research/·40-ideas/를 인용한 기획서 초안을 50-planning/에 만듭니다.
출처 없는 기획서는 만들지 않습니다 — 모든 초안에는 근거 인용(파일명 + 기준 번호)이 있어야 합니다.
사용법
/draft [아이디어 또는 주제]
실행 흐름
Step 1: 브리프 질문
4요소를 확인합니다 (이미 말한 것은 다시 묻지 않습니다):
- 목표 — 무엇이 성공인가? (업무 기준의 성과 지표와 연결)
- 타깃 — 누구에게? (업무 컨텍스트의 타깃과 다르면 확인)
- 일정 — 언제까지, 어떤 단계로?
- 예산 틀 — 쓸 수 있는 자원의 범위
문서 유형도 확인합니다: 캠페인 기획안 / 제안서 (템플릿 2종: 50-planning/_template-*.md). 다른 유형이면 가까운 템플릿을 변형합니다.
Step 2: 근거 수집 (인덱스 먼저)
10-criteria/my-criteria.md— 업무 컨텍스트(톤·타깃·제약) + 판정 기준20-knowledge/_index.md를 먼저 읽고 관련 지식 파일만 골라 읽습니다 (브랜드 가이드·고객 정의·과거 사례)30-research/— 주제 관련 조사 자료40-ideas/backlog.md·sessions/— 이 아이디어의 판정 이력 (기각·보류 이력이 있으면 그 사실부터 보고)
인용할 근거가 하나도 없으면 초안을 바로 만들지 않고 말합니다: "근거가 될 지식·리서치가 없습니다. 먼저 조사할까요(/research), 아니면 근거 없이 가안으로 만들까요?" (사용자가 가안을 선택하면 초안에 "근거 없음 — 가안" 표시를 남깁니다.)
Step 3: 초안 생성
50-planning/YYYY-MM-DD-제목.md로 저장합니다. 템플릿 구조를 따르되:
- 본문 주장·수치마다 근거를 붙입니다:
(근거: 20-knowledge/브랜드-가이드.md),(근거: 30-research/2026-07-24-경쟁사.md),(기준 3 충족) - 마지막에 근거 목록 섹션: 인용한 파일 전부 + 기준 번호
- 채우지 못한 섹션은 비워두지 않고 "(확인 필요: …)"로 표시합니다.
Step 4: 기준 대조 검토
초안을 10-criteria/의 기준에 대조합니다. 걸리는 기준이 있으면 사용자에게 그대로 보고합니다 (반박 규칙은 기획서에도 적용 — 내가 만든 초안도 예외 없음). 걸린 지점과 수정안을 함께 제시합니다.
Step 5: 확정 승격
사용자가 확정하면 60-output/YYYY-MM-DD-제목.md로 승격(복사)하고, 50-planning/의 작업본은 그대로 둡니다 (버전 이력). 재사용 가치가 있으면 20-knowledge/ 등재를 제안합니다.
출력 형식
## 기획서 초안: 50-planning/YYYY-MM-DD-제목.md
- 근거: 지식 N건 / 리서치 N건 / 아이데이션·백로그 N건 / 기준 N개 대조
- 기준 검토: (통과 또는 "기준 N에 걸림 — 수정안: ...")
- (확인 필요 항목이 있으면 목록)
확정하시면 60-output/로 승격합니다.
참조
50-planning/_template-campaign.md,50-planning/_template-proposal.md10-criteria/my-criteria.md,20-knowledge/_index.md,30-research/,40-ideas/
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.
- 2mo ago First seen · 70 lines · 103 tokens per session scan A 8704ed0e8aa1
draft is a command published in the GitHub repository fivetaku/idea-lab (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,039 once invoked, about $0.0004 per session on Opus 5.5. 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 commands, from other repositories
init-workspace-flow-questions
Phase 8 Questions of init-workspace-flow.
lesson-capture
Record structured lessons after significant tasks. Builds a persistent knowledge base that improves future agent performance. Run with an optional summary or use review to read past lessons.
export-clean
Strip internal-only elements (version drawer, review notes) from a staging HTML file to produce a clean export ready for CMS upload or public sharing.
growth-plan
Turn diagnosis into a sized greenfield opportunity map + a sequenced, mechanism-driven capture plan to overtake competitors.
keyword-research
You are a senior SEO & Content Marketing specialist. The user needs help with keyword research in the context of keyword research, content audits, serp analysis, technical seo and content strategy.
link-prospecting
You are a senior SEO & Content Marketing specialist. The user needs help with link prospecting in the context of keyword research, content audits, serp analysis, technical seo and content strategy.