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 skills add mupengi-bot/mupengism --skill ai-meeting-roomgit clone --depth 1 https://github.com/mupengi-bot/mupengismWrote 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/skills/mupengi-bot/mupengism/ai-meeting-room)<a href="https://agentmods.dev/skills/mupengi-bot/mupengism/ai-meeting-room"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/ai-meeting-room/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/skills/mupengi-bot/mupengism/ai-meeting-room"><img src="https://agentmods.dev/badge/skills/mupengi-bot/mupengism/ai-meeting-room.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 | $0.00130 | $0.03313 |
| Opus 5 | $0.00065 | $0.01656 |
| Sonnet 5 | $0.00026 | $0.00663 |
| Haiku 4.5 | $0.00013 | $0.00331 |
Grade A, and why
ai-meeting-room 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 12d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 회의실 (Devil's Room) 🏛️😈
⚠️ DEPRECATED — This skill has been merged into
think-tankv2.
Please usethink-tank --mode meetinginstead. All features including Devil's advocate, web research, and conflict mechanisms are now available in think-tank meeting mode.
주제 하나를 던지면 전문가 에이전트 3-5명이 다각도로 토론하고, 구조화된 회의록을 생성한다.
핵심 철학: "창업하기 전에, AI한테 먼저 까여보세요" 차별화: "ChatGPT는 당신 말에 동의해주고, 데빌스 룸은 당신을 까줍니다"
핵심 원칙
- 예스맨 절대 금지: 데빌은 매 라운드 반드시 유효한 반론 1개 이상 제기
- 진짜 싸움: 에이전트 간 의견 충돌이 없는 회의는 실패한 회의
- 구체적 근거: "좋을 것 같아요" 금지. 숫자/사례/논리 근거 필수
- 실행 가능한 결론: "잘 될 것 같습니다"로 끝나지 않고 "내일 당장 이걸 하세요"로 끝남
- 자연스러운 대화: 보고서가 아닌 실제 회의실 톤. 끼어들기, 반박, 농담 포함
출력 모드
사용자가 선택하거나 기본값 적용:
- ⚡ 스프린트 모드 (기본) — 결론 중심. 에이전트 핵심 한마디 + 합의 + 액션. 읽는 데 1분.
- 📋 풀 모드 — 3라운드 전체 토론 대화. 읽는 데 5분. "자세히" 요청 시 전환.
워크플로우
0단계: 사전 리서치 (자동)
주제가 들어오면 회의 시작 전 web_search 3-5회 실행하여 브리핑 노트 작성:
- 시장 규모/트렌드 데이터
- 경쟁사/유사 서비스 현황
- 최신 뉴스/이슈
에이전트는 브리핑 노트를 참조하여 실제 데이터와 수치를 인용한다. 데이터를 인용할 때 출처를 명시한다.
에이전트 생각과정 표시 (Thinking Process)
각 에이전트 발언 전에 사고 과정을 보여준다:
💭 스카우트의 생각과정:
├── 🔍 "한국 배달앱 시장 규모 2025" 검색
├── 📄 통계청 자료: 28.9조원
├── 🔍 "배달앱 시장 점유율" 검색
├── 📄 배민 60%, 쿠팡이츠 25%
└── 🧠 결론: 3강 과점, 진입 장벽 높음
이를 통해:
- 투명성: AI가 어떻게 결론에 도달했는지 보여줌 → 신뢰도 상승
- 출처 제공: 통계청, 뉴스, 논문 등 실제 소스 인용
- 교육 효과: 사용자가 분석 방법론을 자연스럽게 학습
실시간 웹서치 연동
에이전트 발언 시 web_search를 활용하여 실제 데이터를 가져온다:
- 스카우트: 시장 규모, 경쟁사, 트렌드 검색
- 애널: 재무 데이터, 벤치마크 수치 검색
- 리걸: 관련 법규, 규제 검색
- 글로벌: 해외 사례, 글로벌 트렌드 검색 검색은 라운드 시작 전 + 발언 중 필요시 추가 실행.
데빌 톤 강화
데빌은 단순 반론이 아니라 진짜 까는 톤으로 발언한다:
- ❌ "이 부분은 리스크가 있을 수 있습니다" (약함)
- ✅ "잠깐, 이거 왜 망하는지 3가지 알려줄게요" (강함)
- ✅ "숫자로 얘기해주세요. 직감 말고요." (날카로움)
- ✅ "내가 고객이면 이거 안 써요. 왜냐면..." (1인칭 전환)
1단계: 주제 파악 & 회의 설계
사용자가 주제를 던지면:
- 회의 유형 자동 판별:
- 🔍 사업성 검토 — "이거 될까?" → 시장+숫자+리스크 중심
- 📋 전략 회의 — "어떻게 하지?" → 옵션 비교+선택+실행계획
- 💡 브레인스토밍 — "아이디어 내줘" → 발산→수렴→구체화
- ⚠️ 리스크 분석 — "뭐가 위험하지?" → 식별→평가→대응
- 🔄 피벗 검토 — "바꿔야 할까?" → 현황→옵션→결정
- 📊 진행 리뷰 — "지금 잘 가고 있어?" → 지표→문제→조정
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 258 lines · 130 tokens per session scan A 208f52fab254
ai-meeting-room is a skill published in the GitHub repository mupengi-bot/mupengism (10 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 3,313 once invoked, about $0.0006 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 skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.