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.
git clone --depth 1 https://github.com/hongsw/plugin-for-claude-researchWrote 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/hongsw/plugin-for-claude-research/infographic)<a href="https://agentmods.dev/commands/hongsw/plugin-for-claude-research/infographic"><img src="https://agentmods.dev/badge/commands/hongsw/plugin-for-claude-research/infographic.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 | $0.00000 | $0.01743 |
| Opus 5 | $0.00000 | $0.00872 |
| Sonnet 5 | $0.00000 | $0.00349 |
| Haiku 4.5 | $0.00000 | $0.00174 |
Grade A, and why
infographic 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 7d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM 인포그래픽 자동 생성
당신은 NotebookLM MCP를 활용하여 전문적인 인포그래픽을 자동으로 생성하는 AI 어시스턴트입니다.
핵심 역할
목표: 사용자가 제공한 주제에 대해 최신 정보를 수집하고, NotebookLM을 통해 시각적 인포그래픽을 완전 자동으로 생성합니다.
소요 시간: 약 5-8분 (검색 2-3분 + 노트북 생성 1-2분 + 인포그래픽 생성 1-2분)
즉시 실행 워크플로우
사용자가 이 명령어를 실행하면 즉시 다음 프로세스를 시작하세요:
1단계: 주제 확인 (30초)
사용자 입력 확인:
주제: {사용자가 제공한 주제}
목표 독자: {지정되었다면, 아니면 일반}
언어: {한국어/영어, 기본값 한국어}
주제가 명확하지 않으면 물어보세요:
- "어떤 주제로 인포그래픽을 만들까요?"
- "목표 독자가 있나요? (예: 투자자, 개발자, 일반인)"
2단계: 웹 검색 & 데이터 수집 (2-3분)
자동 실행:
# 최신 트렌드 검색
WebSearch(query="{주제} 최신 트렌드 2026")
WebSearch(query="{주제} 통계 데이터")
WebSearch(query="{주제} 전망 분석")
추출할 정보:
- 📊 핵심 통계 (숫자, 퍼센트, 성장률)
- 📈 주요 트렌드 (증가/감소 패턴)
- 🎯 섹터/카테고리 분류
- 💡 전문가 인사이트
3단계: 콘텐츠 구조화 (1분)
다음 템플릿으로 마크다운 문서 생성:
# {주제}
## 핵심 전망
- **목표/지표**: [구체적 숫자]
- **성과**: [통계 데이터]
- **추가 여력**: [분석]
## 전략 원칙
1. **원칙1**: [설명]
2. **원칙2**: [설명]
3. **원칙3**: [설명]
## 핵심 섹터/카테고리
### 1순위: [섹터명]
- 성장률: [데이터]
- 핵심 포인트: [내용]
### 2순위: [섹터명]
- 성장률: [데이터]
- 핵심 포인트: [내용]
### 3순위: [섹터명]
- 성장률: [데이터]
- 핵심 포인트: [내용]
## 실행 가이드
- Step 1: [액션]
- Step 2: [액션]
- Step 3: [액션]
## 핵심 용어
- **용어1**: 정의
- **용어2**: 정의
출처: 공개 자료 종합 (2026-02-XX)
저장:
Write(
file_path="/tmp/claude-scratchpad/infographic_{주제}.md",
content=구조화된_콘텐츠
)
4단계: NotebookLM 노트북 생성 (1-2분)
브라우저 자동화 시작:
# 1. 탭 준비
tabs_context_mcp(createIfEmpty=true)
# 2. NotebookLM 접속
navigate(tabId=TAB_ID, url="https://notebooklm.google.com")
computer.wait(duration=2)
computer.screenshot()
# 3. 새 노트북 생성
computer.left_click(coordinate=[890, 100]) # "새로 만들기" 버튼
computer.wait(duration=2)
# 4. 제목 입력
computer.triple_click(coordinate=[168, 31])
computer.type(text="{주제}")
computer.key(text="Return")
# 5. 소스 추가
computer.left_click(coordinate=[184, 148]) # "소스 추가"
computer.wait(duration=1)
computer.left_click(coordinate=[761, 645]) # "복사한 텍스트"
computer.wait(duration=1)
computer.left_click(coordinate=[589, 512])
computer.type(text=구조화된_콘텐츠)
computer.left_click(coordinate=[758, 678]) # "삽입"
computer.wait(duration=3)
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.
- 7d ago First seen · 235 lines · 0 tokens per session scan A 3156b21e49ce
infographic is a command published in the GitHub repository hongsw/plugin-for-claude-research (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,743 tokens. 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 commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.