AI advisors debate your business decision in Claude Code

A GitHub project called roast-room lets users convene a council of AI advisors inside Anthropic's Claude Code to debate a business decision and return a scored verdict plus a downloadable PDF. The tool ships with 12 advisors built from each person's public letters, essays, talks and videos — a seven-seat default board (Jeff Bezos, Paul Graham, Alex Hormozi, Gary Vaynerchuk, Dan Martell, Gino Wickman, Warren Buffett) and five on-call advisors (Naval Ravikant, Codie Sanchez, Leila Hormozi, Sara Blakely, Elon Musk) — and runs on Node.js 20 or newer via `npm start` at localhost:4730, with no API key needed beyond a Claude plan. Users type `/roast-room` with their decision, options, numbers, limits and lean, and can add advisors with `/newroaster`, run a four-advisor two-round `--quick` session, or restrict seats with `--seats`; the full report is written to `sessions/<date>-<decision>/verdict.md`.

Bring a hard business decision and a council of AI advisors argues it out, then hands you a scored verdict and a one-click PDF. Twelve advisors ship with it, each built from that person's public work: their letters, essays, talks, and videos. For each question, the Chair recommends who should sit on the council and you confirm. The council runs in Claude Code, and a small local web app shows them around a table talking it through. Want someone else at the table? Type /newroaster and a name, and Claude builds that advisor the same way. | Seat | Pillar | The question they own | |---|---|---| | Jeff Bezos | Strategy and decisions | Is this the right bet, and how reversible is it? | | Paul Graham | Product and startups | Do people actually want this, and is it growing? | | Alex Hormozi | Offers, pricing, and sales | Will people pay, how much, and how do we close? | | Gary Vaynerchuk | Marketing and attention | Where does the attention come from? | | Dan Martell | People, hiring, and founder time | Who does this, and what does it cost your calendar? | | Gino Wickman | Operations and scaling | Can the business run this without you holding it together? | | Warren Buffett | Money and capital | What does it do to cash, risk, and long-term value? | Those seven are the default board . Five more advisors are on call, and the Chair brings them in when your question is in their lane: | Seat | Pillar | The question they own | |---|---|---| | Naval Ravikant | Leverage and wealth | Does this build leverage and equity you own, or does it just rent out your time? | | Codie Sanchez | Buying and owning small businesses | Should you build this, or buy something that already works? | | Leila Hormozi | Leadership and scaling teams | Can your team and your leadership carry this, and who has to change? | | Sara Blakely | Consumer product and brand from zero | Will customers love it enough to sell it for you, without outside money? | | Elon Musk | First principles and execution speed | What is the real constraint here, and can we cut steps and build it faster? | - Claude Code https://claude.com/claude-code . Your Claude plan covers it; no API key needed. - Node.js https://nodejs.org 20 or newer, for the room. There's nothing to install beyond that. git clone https://github.com/nateherkai/roast-room.git cd roast-room Or open Claude Code anywhere and say: "Clone github.com/nateherkai/roast-room and start the room for me." 1. Start the room: npm start , then open http://localhost:4730 http://localhost:4730 . Leave it open. 2. Open Claude Code in the same folder: claude 3. Type /roast-room and your decision. 4. Answer the Chair's questions, then watch the council argue it out in the room. 5. When the verdict lands, click Download PDF . You also get a short verdict in Claude Code, and the full report lands in sessions/<date -<decision /verdict.md . The council is only as good as what you give it. Include: - The decision in one line. - Your options. Two or three. "Keep doing what I do now" counts. - Your numbers. Revenue, cash, and team size. - Your limits. Deadline, hours, and budget. - What success looks like , and by when. - Which way you're leaning , and why. The council tests your lean instead of agreeing with it. Left something out? The Chair asks before the council starts. Example: /roast-room I run a coaching business at $30k a month with 15 clients at $2,000 each. Should I raise to $3,500 for everyone, raise for new clients only, or keep $2,000? Close rate is about 50% and I have $40k in the bank. Success is $45k a month by March. I'm leaning toward raising for everyone because I'm underpaid. More ways to run it: - /roast-room --quick ... seats four advisors for two rounds. Use it for smaller, reversible calls. It uses far less of your plan. - /roast-room --seats hormozi,buffett ... seats only the advisors you name. - /roast-room ask hormozi ... gets one answer from one seat. - /roast-room --all ... seats every advisor you have up to nine . - /roast-room board shows who sits at the table by default and lets you change it. The room is optional. The council runs the same in Claude Code without it. When you run /roast-room , the Chair reads your question and recommends a council from every advisor you have, with one line on why each one fits. You pick: - Recommended board : the five to seven advisors the Chair picked for this question. - Default board : your usual seven. - Everyone : all of them, when you have nine or fewer. - Other : type changes, like "recommended, but add Naval and drop Wickman". A pricing question might get Hormozi, Buffett, Codie Sanchez, Sara Blakely, and Graham. A hiring question might get Leila Hormozi, Martell, Wickman, Naval, and Buffett. Every council keeps a seat that guards your downside and one that's likely to disagree, so the room argues instead of nodding. How the board gets picked is a setting in .claude/skills/roast-room/roster.json : { "board": "ask", "default": "bezos", "graham", "hormozi", "garyvee", "martell", "wickman", "buffett" , "seats": ...every advisor you have... } | Setting | What happens on every /roast-room | |---|---| | "ask" out of the box | The Chair recommends a council and asks you to confirm it. | | "auto" | The Chair picks the council and tells you who and why, without asking. | | "default" | Your default board sits every time. No question. | You don't need to edit the file by hand. Type /roast-room board and say what you want: "put Naval on my default board", "take Gary V off", or "stop asking me, just use my default board". Skip the question on any run: --seats hormozi,naval,buffett seats exactly those advisors, and --all seats everyone up to nine . --quick recommends four. /newroaster Morgan Housel Claude builds a new seat the way the original seven were built: 1. Asks two or three questions : the business pillar and question the advisor owns it suggests one , whether they join your default board, and how deep to go. 2. Finds their public work : essays, letters, talks, long interviews, and podcasts where they are the main speaker. 3. Fetches it into build/<name / , a local folder git ignores. Web pages become text and YouTube videos become transcripts. 4. Extracts how they think : parallel sub-agents read every source and pull out their frameworks, rules, positions, stories, and voice, with verbatim quotes. 5. Writes the brain .claude/skills/roast-room/brains/<name / and checks that every quote is word for word in the source it cites. 6. Writes the advisor's agent .claude/agents/council-<name .md and adds them to roster.json . 7. Makes their portrait for the room from a real photo, in the same cartoon style as the other advisors. 8. Tests the new seat on a sample question, then tells you how to use it. | Depth | Sources | Good for | |---|---|---| | --quick | 12 to 20 | Trying someone out | | default | 30 to 50 | An advisor you'll use | | --deep | 80+ | Matching the original seven | A standard build is about 8 to 10 sub-agent runs, so it uses a real share of your plan. When it finishes, open a new Claude Code session so the advisor loads as its own agent the council works before that too . Then use them like anyone else: /roast-room ask housel ... , /roast-room --seats housel,buffett,hormozi ... , or put them on your default board. The Chair also starts recommending them when a question fits their pillar. You can build an advisor from public figures, living or historical, with a real body of public work, or from your own material your posts, transcripts, notes if you want yourself or a consenting mentor on the board. The raw sources stay on your machine; only the brain, which holds short quotes and paraphrase, is meant to be committed. Their face in the room: /newroaster also makes the new advisor's cartoon portrait, the same way the original seven were made. It finds a real photo of the person, turns it into the same 3D cartoon style using one of the existing cartoons as the style reference , picks the closest likeness, and makes the talking frames mouth open, mouth "oh", and a blink . This step needs a kie.ai https://kie.ai/api-key key in .env KIE AI API KEY= , about 5 image jobs per advisor and Python with opencv-python Claude installs it if it's missing . Without a key the advisor still works and shows a placeholder face; add a key later and run /newroaster portrait <name . YouTube transcripts and photos work best with yt-dlp https://github.com/yt-dlp/yt-dlp installed, and PDFs need pdftotext Poppler https://poppler.freedesktop.org . Both are optional: without them, Claude falls back to YouTube's own captions and reads PDFs itself. Run npm start , open http://localhost:4730 http://localhost:4730 , and click Past sessions . Three finished councils ship with the repo, so you can see how it works and download their PDFs before you run your own. - The council runs in Claude Code. Each seat is a sub-agent .claude/agents/council- .md , listed in roster.json that reads its own brain .claude/skills/roast-room/brains/<name / : frameworks, principles, positions, stories, and voice notes compiled from public sources, with every quote tied to a source. Claude Code acts as the Chair. It runs the rounds, keeps score, and writes the verdict .claude/skills/roast-room/SKILL.md . - Each seat scores every option , weighted by how much that seat's pillar matters to your decision. The Chair caps the verdict when a seat flags ruin risk, and it forces a real argument when everyone agrees too fast. - The room only watches. As the Chair works, it writes each step to sessions/ , and the app plays those files back. Between rounds it shows which round is running, how long it has been, and what each advisor is weighing. The room makes no AI calls of its own. - Every council is saved in sessions/ . Past sessions replays any of them and downloads its PDF. - Usage: a full council is three sub-agent runs per seat 21 for seven , so it takes a real bite out of your plan's usage. Use --quick for small calls. If you'd rather type a decision straight into the room, copy .env.example to .env , add an ANTHROPIC API KEY , set COUNCIL RUNNER=api , and restart npm start . That mode bills your Anthropic API account about 25 calls per full council . | Path | What | |---|---| | .claude/skills/roast-room/ | The council skill: protocol, prompts, scoring, report template, and one brain per advisor | | .claude/skills/roast-room/roster.json | Every advisor, your default board, and how the board is picked | | .claude/skills/newroaster/ | The /newroaster skill and its scripts: fetch sources, check quotes, register a seat | | .claude/agents/ | One agent per advisor council-<name .md | | app/ | The room: a zero-dependency Node server, the web page, and the PDF builder | | sessions/ | Your councils kept out of git and the three examples | | build/ | Raw sources /newroaster fetched kept out of git | These are simulations built from each person's public work, and so is any advisor you add. They are not the people, they don't speak for them, and none of them is affiliated with or endorses this project. A seat only quotes a person verbatim when the line is in its brain with a source, and python .claude/skills/roast-room/scripts/check quotes.py sessions/<session checks every quote in a council against the brains. Each brain's sources.md lists what it was built from. Built by AI Automation Society. The code is MIT licensed; see LICENSE . The PDF builder bundles jsPDF https://github.com/parallax/jsPDF MIT and Montserrat https://github.com/JulietaUla/Montserrat SIL Open Font License ; their licenses sit next to them in app/public/ .