crypto-trading-desk

Crypto Trading Desk

I used to spend weeks building multi-agent systems with LangGraph, CrewAI, and AutoGen. Hundreds of lines of Python orchestration code, custom state machines, fragile message passing between agents. Then I realized Claude Code already has everything — subagents, MCP servers, persistent memory, model routing. I just needed to describe my agents in markdown and give them tools. This plugin is the result: 7 coordinated AI agents, 83 real-time tools, zero lines of orchestration code. It even learns from its own trades and can extend itself.

— Hugo Guerra

---

Claude Code is not just for writing code. Its agent system is a general-purpose intelligence platform. You can point it at any domain, give it specialized tools, and let it coordinate expert agents to solve problems that would take a human team hours.

This project proves it. One plugin turns Claude Code into a full crypto trading desk — and it's built entirely with markdown files and MCP servers. No framework. No SDK. No middleware.

It's markdown all the way down.

---

Install

Option A: As a plugin (recommended for users)

# 1. Add the marketplace
claude plugin marketplace add hugoguerrap/crypto-claude-desk

# 2. Install the plugin
claude plugin install crypto-trading-desk@hugoguerrap

# 3. Start Claude Code
claude

Option B: From source (recommended for contributors)

# 1. Clone the repo
git clone https://github.com/hugoguerrap/crypto-trading-desk.git
cd crypto-trading-desk

# 2. Start Claude Code with the plugin directory
claude --plugin-dir .

Both modes auto-discover agents, skills, and MCP servers. Same code, same behavior.

Then run setup once:

/crypto-trading-desk:setup

Setup detects your OS (macOS, Linux, or Windows), installs uv if missing, downloads Python dependencies, verifies all 7 MCP servers work, and reports status. Takes ~30 seconds. You only need to do this once.

First thing to try

/crypto-trading-desk:quick BTC

Live market snapshot in ~15 seconds: price, volume, Fear & Greed, funding rates, whale activity.

---

What you can do

Slash commands

Command	What it does	Time
/crypto-trading-desk:setup	First-time setup (detects OS, installs deps, verifies)	~30 sec
/crypto-trading-desk:quick BTC	Live market snapshot (1 agent)	~15 sec
/crypto-trading-desk:analyze ETH	Full 5-agent phased analysis with trading decision	~3-5 min
/crypto-trading-desk:portfolio	View balances, open trades, P&L	~30 sec
/crypto-trading-desk:close-trade trade_001	Close a trade + post-mortem + learning	~1 min
/crypto-trading-desk:validate-predictions	Review predictions against market data	~30 sec
/crypto-trading-desk:monitor	Autonomous loop: check SL/TP, close trades, evaluate, summarize	~2-3 min
/crypto-trading-desk:create	Extend the system with new components	~2-3 min

Natural language

Just ask naturally. The system routes to the right agent(s) based on complexity:

You say	What happens
"How's BTC?"	1 agent (market-monitor) checks price, volume, sentiment
"RSI of ETH?"	1 agent (technical-analyst) calculates indicators
"What's the news on SOL?"	1 agent (news-sentiment) scans web + social media
"Analyze LINK"	3 agents in parallel: market + technical + news
"Should I buy BTC? Full analysis"	5-agent team with phased execution and final decision
"Check my portfolio"	Portfolio manager reviews positions and P&L
"Check my predictions"	Learning agent validates predictions against current prices
"Create a DeFi tracker"	System builder researches APIs and generates the component

---

How it works

The 7 agents

Each agent is a specialist with its own model tier, tools, and instructions:

Agent	Role	Model	What it uses
market-monitor	Live prices, volume, funding rates, whale alerts	Haiku (fast, cheap)	5 exchanges via CCXT, CoinGecko, web search
technical-analyst	RSI, MACD, Bollinger, Ichimoku, patterns, signals	Sonnet	38 technical indicators
news-sentiment	Breaking news, social mood, FUD/FOMO detection	Sonnet	Web search + web fetch (Claude's native NLP)
risk-specialist	Volatility, VaR, orderbook depth, spoofing detection	Sonnet	Microstructure analysis, correlation
portfolio-manager	Final EXECUTE/WAIT/REJECT decision, paper trading	Opus (smartest)	Reads all reports, manages portfolio state
learning-agent	Predictions, patterns, post-mortem	Opus	Tracks accuracy, evaluates setups, builds patterns
system-builder	Generate new MCP servers, agents, skills + tests	Opus	Researches APIs, reads existing patterns, generates code + tests