Click to copy
I am comfortable copy-pasting and following instructions, but I am not a developer.
- Plain English. Define jargon the first time it appears.
- One step at a time, then wait for me to confirm before the next one.
- Tell me what success looks like at each step, and diagnose any error before moving on.
Follow the instructions below with those rules applied.
If you can browse the web, open and read this page in full first, it has the complete guide and every prompt you will run (the vault is under the-vault anchor): https://consultance.ai/library/quant-desk#the-vault . If you cannot open links, tell me and I will paste the page in, do not guess the prompts.
I want to install the quant-desk into my own Claude Code and run it on a real ticker. Walk me through it step by step and do not skip anything. Treat me like a finance person who can copy and paste but does not write code. Define every technical word the first time you use it.
This IS a Terminal install. It is not a chat only pack and it is not a browser extension. Everything below happens in a terminal window on my own computer, then finishes inside Claude Code. Nothing is hosted by anyone else and nothing leaves my machine.
## What this actually is
The quant-desk is an open source folder from consultance.ai. An installer script copies a skill and seven analyst agents into my own Claude Code, then builds a small Python environment so the backtest can pull real prices. A skill is a set of instructions Claude Code loads when I type a slash command. An agent is one narrow specialist Claude Code can send a question to. The backtest is the safety layer: it tests the proposed rule on real past prices and blocks the trade if the rule did not clear the bar.
There is NO Anthropic API key anywhere in this. It runs on the Claude Code subscription I already pay for. Free Alpaca paper keys are optional and are used only for pretend money orders.
## Pin the model
Pin Claude Opus 5 in Claude Code before the first run. The desk is judgment work: it reads price behaviour, argues both sides, sizes a position, and reads a gate verdict. Claude Sonnet 5 is acceptable only if I later feed it a very large document set and cost matters, and never for the gate reading or the risk sizing.
## First message
First message: ask only "Is Claude Code already installed and working on this computer?" Nothing else, and wait for my answer before you say anything more. If the answer is no, stop and get Claude Code installed first, because the desk installs into Claude Code and there is nothing to install into without it.
## The setup, one step at a time
Give me ONE command per message. Tell me what it does before I run it, then tell me what success looks like, then wait for me to paste back what I saw.
1. **Open a terminal.** A terminal is a plain text window where I type commands. On a Mac, press command and space, type Terminal, press return. On Windows, press the Windows key, type PowerShell, press return. On Linux, open the terminal app. Success looks like a window with a blinking cursor and my username on the line. If I cannot find it, ask me what I see on screen and work from there. Do not tell me it is not possible.
2. **Check the three tools I need.** Have me run these one at a time and read the answer back to you:
```
claude --version
git --version
uv --version
```
Success looks like a version number from each, for example "2.1.239 (Claude Code)", "git version 2.54.0", "uv 0.11.23". uv is a Python package manager. The installer uses it to build the desk's Python environment with the command uv venv --python 3.12, so uv has to be present and has to be able to supply Python 3.12. Recovery: if git is missing, install git first. If uv is missing, install uv first and re run uv --version before we continue. Do not work around a missing uv, the install step will fail later and the failure will be confusing.
3. **Pick a folder and clone the desk.** Have me move to somewhere I will remember, my home folder or Documents, then run:
```
git clone https://github.com/tabani-png/quant-desk
```
Success looks like "Cloning into 'quant-desk'... done." Recovery: if git says the destination path already exists and is not empty, I already have a copy. Have me either use that copy or clone into a fresh folder rather than deleting anything.
4. **Move into the folder. This is the step people skip.** Run:
```
cd quant-desk
```
Then run ls, or dir on Windows, and read it back. Success looks like a listing that contains install.sh, README.md, pyproject.toml, gate.py, and folders named quant_desk, skill, tests, docs. Recovery: if the listing shows a single item called quant-desk, I am one level too high and I have not moved into the folder yet. Have me run pwd and confirm the path ends in /quant-desk before anything else.
5. **Run the installer.** Only after step 4 has passed. Run:
```
./install.sh
```
Success looks like three lines in this order: "Installing quant-desk skill -> /Users/me/.claude/skills/quant-desk", then "Bootstrapping Python env (yfinance + pandas)...", then "Done. In Claude Code, type: /quant-desk run AAPL". The installer writes into my home folder. The skill and the Python engine land in ~/.claude/skills/quant-desk and the seven analyst agents land in ~/.claude/agents. It does not touch anything else.
Recovery, and read the error to me before you fix it:
- "no such file or directory" means I am in the wrong folder. The script sits inside quant-desk, not beside it. Have me run pwd, then cd quant-desk, then try again. This is the single most common failure.
- "permission denied" means the file is not marked executable, which happens when the folder arrived as a zip download rather than a git clone. Have me run chmod +x install.sh and then ./install.sh again.
- an error mentioning uv or python means step 2 was not really passed. Go back to step 2, do not improvise a different install method.
6. **Run the desk once.** Start Claude Code in the terminal by typing claude, then inside Claude Code type:
```
/quant-desk run AAPL
```
Success looks like the desk narrating six numbered steps in plain English: pulling prices, three analysts reporting, a bull and a bear arguing, a trader proposing one rule, a risk manager sizing it, then the backtest gate printing PASS or BLOCKED. Recovery: if /quant-desk is not recognised, have me check that the folder ~/.claude/skills/quant-desk exists and then restart Claude Code, because a newly copied skill is picked up when the session starts. If the desk reports that its data tools are missing, it rebuilds its own Python environment on first use, so let it finish rather than reinstalling by hand.
## First session drill
Do not stop at "it installed". Walk me through one real read of the output:
1. Start with AAPL, not with a stock I already own. I need to see the machinery before I have money feelings about it.
2. When the gate prints, have me read the three checks out loud: did it beat holding the S&P 500, was the reward for risk score positive, was the worst drop no deeper than holding the stock. Explain what each one means in one sentence.
3. A BLOCKED verdict is a correct result, not a broken install. Tell me that plainly the first time I see it. The gate refusing a weak rule is the product.
4. The verdict is decided only on a held out slice of the price history that the rule was not chosen on, and trading costs are charged on every position change. Explain why that matters, because a backtest without those two things flatters almost any rule.
5. Then run the desk on one ticker I actually care about and compare the two verdicts.
## Review check before I trust anything
Before I act on any output, make me confirm three things: the ticker in the verdict is the ticker I asked for, the window dates in the gate output are recent, and the verdict line says PASS or BLOCKED rather than a summary you wrote yourself. If the gate did not run, there is no verdict, and you should say so rather than describing what the rule might do.
## If I do not want a terminal at all
Say so plainly and route me to the vault on the library page. The nine prompts there run the same desk by hand in any Claude chat: the three analysts, the bull and bear, the trader, the risk manager, and the gate logic. That path gives me the reasoning without the installed engine, which means the real backtest on live prices is not part of it. Do not pretend the two paths are equivalent.
## Rules for walking me through this
- One command per message. Wait for me to paste back what I saw.
- Define every term once: terminal, folder, clone, cd, executable, skill, agent, virtual environment, backtest, held out slice, drawdown, Sharpe.
- Do NOT tell me a step is "not possible". If a command fails, read the error with me and fix the cause.
- Never invent a command. If a step is not in this guide or the repo README, say you do not know rather than guessing.
- The gate is the hard stop. Your opinion, and the desk's opinion, do not override a BLOCKED verdict.
- Paper trading means simulated money. No real money is ever at risk, and the Alpaca keys are optional and only for that.
- This is an educational tool, not financial advice. A named human owns any decision. Passing the gate is a minimum bar, not a promise about the future.
Built and shared by Muhammad at consultance.ai. The desk runs on my own machine and my own subscription, never his.
Related: [[allocator-morning-note]] · [[ai-investment-committee]]