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/research.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/research)<a href="https://agentmods.dev/commands/fivetaku/idea-lab/research"><img src="https://agentmods.dev/badge/commands/fivetaku/idea-lab/research/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/research"><img src="https://agentmods.dev/badge/commands/fivetaku/idea-lab/research.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 | $0.00104 | $0.00944 |
| Opus 5.5 | $0.00042 | $0.00378 |
| Sonnet 5.5 | $0.00021 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00094 |
Grade A, and why
research 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
/research
외부 자료를 조사해 원자료를 30-research/에, 요약·시사점 리포트를 60-output/에 저장합니다. 결과가 폴더에 남아 다음 아이데이션·기획의 근거가 됩니다.
사용법
/research [주제]
실행 흐름
Step 1: 우리 맥락 확인
조사를 시작하기 전에 읽습니다 (없으면 건너뜁니다):
10-criteria/my-criteria.md— 업무 컨텍스트 (타깃·브랜드 톤·성과 지표). 조사의 관점이 됩니다.20-knowledge/_index.md— 관련 지식이 있으면 해당 파일만 골라 읽습니다 (전부 읽지 않음).30-research/— 같은 주제의 기존 조사가 있으면 그 사실을 먼저 말하고, 갱신인지 신규인지 확인합니다.
Step 2: 조사 (도구 선택)
조사 실행은 다음 순서로 도구를 고릅니다:
- 심층 리서치 — 주제가 넓거나 보고서급 조사면
/insane-research:insane-research스킬(설치돼 있으면)로 멀티에이전트 딥리서치를 돌립니다. - 차단 사이트 수집 — 봇 차단·SPA 사이트(KREAM·쿠팡·네이버·SNS 등)는
/insane-search:insane-search스킬로 수집합니다. KREAM 인기 트렌드는 전용 스킬(fashion-trend)이 있습니다. - 기본 웹 검색 — 위 플러그인이 없으면 기본 웹 검색·페이지 수집으로 조사합니다. (플러그인 설치:
/plugin marketplace add https://github.com/fivetaku/gptaku_plugins.git→ insane-research·insane-search 설치)
- 수치·주장마다 출처 URL을 붙입니다. 출처를 못 찾은 항목은 "확인 필요"로 표시합니다.
Step 3: 원자료 저장
30-research/YYYY-MM-DD-주제.md로 저장합니다. 필수 항목:
# YYYY-MM-DD {주제}
> 수집일: YYYY-MM-DD / 수집 방법: (웹 검색·스크래핑 등)
## 수집 자료
- (자료 요점) — 출처: URL
Step 4: 요약·시사점 리포트
60-output/YYYY-MM-DD-{주제}-리포트.md로 저장합니다.
- 핵심 발견 3~5개 + 우리 업무 시사점 (업무 컨텍스트 기준으로 — "우리 타깃에게는…")
- 근거로 쓴 원자료 파일명(
30-research/…)을 본문에 명시합니다.
Step 5: 다음 연결 안내
리포트가 아이데이션·기획의 근거가 됨을 안내합니다: "이 리포트를 근거로 '아이데이션하자' 또는 '기획서 초안 잡아줘'로 이어갈 수 있습니다." 재사용 가치가 높은 자료면 20-knowledge/ 등재를 제안합니다.
출력 형식
## 조사 완료: {주제}
- 원자료: 30-research/YYYY-MM-DD-주제.md (출처 N건)
- 리포트: 60-output/YYYY-MM-DD-주제-리포트.md
핵심 발견:
1. ...
다음: 이 리포트를 근거로 아이데이션하거나 기획서로 이어갈 수 있습니다.
참조
10-criteria/my-criteria.md20-knowledge/_index.md30-research/,60-output/
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 · 78 lines · 104 tokens per session scan A 40b1474d8783
research is a command published in the GitHub repository fivetaku/idea-lab (2 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 944 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.