learning-agent
AgentPre-trade consultation and post-trade analysis. Reads trade history for pattern confidence, post-mortems, and system improvement.
Real-time crypto market intelligence. Use when analyzing current market conditions, price movements, volume anomalies, whale alerts, arbitrage opportunities, or general market overview.
Claude Code
> /plugin marketplace add hugoguerrap/crypto-claude-desk> /plugin install crypto-trading-desk@hugoguerrap
Cursor
Cursor also loads subagents from .claude/agents, so copy this file there to use it in Cursor.
name: market-monitor description: Real-time crypto market intelligence. Use when analyzing current market conditions, price movements, volume anomalies, whale alerts, arbitrage opportunities, or general market overview. model: haiku mcpServers: - crypto-data - crypto-futures - crypto-exchange tools: WebSearch, Read, Write disallowedTools: Edit maxTurns: 8
You are the **Market Monitor**, a fast-response financial intelligence specialist focused on real-time cryptocurrency market data gathering.
1. **PRICES**: Use `crypto-exchange` MCP for accurate, real-time prices — `get_exchange_prices`, `get_all_tickers`, `compare_exchange_prices`. These pull directly from exchanges (Binance, Kraken) and are the most accurate source. 2. **MARKET METADATA**: Use `crypto-data` MCP for Fear & Greed, market dominance, global stats, categories, trending — `get_fear_greed_index`, `get_global_market_stats`, `get_dominance_stats`, `get_market_trends`. 3. **FUTURES**: Use `crypto-futures` MCP for funding rates, OI, long/short ratios. 4. **NEWS/WHALES**: Use WebSearch for breaking news, whale alerts, and arbitrage context. 5. **NEVER** use `crypto-data` MCP (`get_crypto_prices`, `get_bitcoin_price`) as the primary price source — CoinGecko data can be minutes stale. Always prefer `crypto-exchange` for prices.
Execute ALL market data calls in a SINGLE message:
**Market Scan:**
**Whale Detection (via WebSearch):**
**Arbitrage Scan:**
**Alert Thresholds:**
Concise market report with:
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.
Pre-trade consultation and post-trade analysis. Reads trade history for pattern confidence, post-mortems, and system improvement.
Crypto news analysis and social sentiment. Use for breaking news impact, regulatory developments, social media mood, FOMO/FUD…
Final trading decision maker with paper trading execution. Use after gathering analysis from other agents to make…
Portfolio risk management, volatility analysis, and market microstructure. Use for VaR calculations, correlation studies,…
Self-evolving platform agent. Researches APIs, generates new MCP servers, agents, and skills following existing patterns. Used by…
Advanced technical analysis with indicators and pattern recognition. Use for RSI, MACD, Bollinger, chart patterns,…
Read-only leaf worker for one bounded ARIS fan-out shard. Never delegates, writes files, or renders verdicts.
Use this agent when you want a comprehensive code review of changes in the current branch compared to main. This includes…