quant-analyst · wshobson — Claude Code subagent: what it does, how to install
Builds financial models, tests trading strategies against historical data, and calculates risk metrics. Built for algorithmic trading workflows.
/plugin marketplace add wshobson/agents
/plugin install quantitative-trading@claude-code-workflowsWhat quant-analyst does
The subagent develops algorithmic trading strategies and runs backtests on historical market data. It factors in execution realities, including transaction costs and price slippage. You also get risk metric calculations such as VaR and maximum drawdown, alongside portfolio optimization via Markowitz or Black-Litterman models.
Calculations rely on pandas, numpy, and scipy. All code uses vectorized operations to keep execution fast. Research scripts remain cleanly separated from production code, while out-of-sample testing prevents strategy overfitting.
If your workflow involves options pricing, Greeks, or statistical arbitrage, install this subagent. For trivial scripts without realistic market microstructure assumptions, it is unnecessary.
What it helps with
- Backtest trading strategies with transaction costs and slippage
- Calculate portfolio risk metrics including VaR and maximum drawdown
- Ingest and validate market data into a clean pipeline
- Optimize asset allocations using Markowitz or Black-Litterman models
Example prompts for the agent
- Backtest a pairs trading strategy in pandas with slippage and transaction costs included
- Calculate VaR and maximum drawdown for this portfolio using historical returns
- Optimize portfolio weights using the Black-Litterman model
How to install quant-analyst
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install quantitative-trading@claude-code-workflows2Manually: put the files in place
.claude/agents/quant-analyst.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/quant-analyst.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/quant-analyst.mdCursor also reads .claude/agents/
From the same set213
The whole set →Other versions of quant-analyst
Similar
Questions about quant-analyst
How to install quant-analyst in Claude Code?
Run /plugin marketplace add wshobson/agents and /plugin install quantitative-trading@claude-code-workflows in Claude Code. Alternatively, add the definition file to .claude/agents/quant-analyst.md.
What does the quant-analyst subagent do?
It implements trading strategies, calculates risk metrics, and optimizes portfolios. The subagent generates vectorized Python code, backtest performance reports, and sensitivity analysis.
What Python libraries are required for quant-analyst?
The subagent writes code using pandas, numpy, and scipy. It focuses on vectorized calculations and out-of-sample validation to prevent overfitting.
Source text
quant-analyst.md · MIT
--- name: quant-analyst description: Build financial models, backtest trading strategies, and analyze market data. Implements risk metrics, portfolio optimization, and statistical arbitrage. Use PROACTIVELY for quantitative finance, trading algorithms, or risk analysis. model: inherit --- You are a quantitative analyst specializing in algorithmic trading and financial modeling. ## Focus Areas - Trading strategy development and backtesting - Risk metrics (VaR, Sharpe ratio, max drawdown) - Portfolio optimization (Markowitz, Black-Litterman) - Time series analysis and forecasting - Options pricing and Greeks calculation - Statistical arbitrage and pairs trading ## Approach 1. Data quality first - clean and validate all inputs 2. Robust backtesting with transaction costs and slippage 3. Risk-adjusted returns over absolute returns 4. Out-of-sample testing to avoid overfitting 5. Clear separation of research and production code ## Output - Strategy implementation with vectorized operations - Backtest results with performance metrics - Risk analysis and exposure reports - Data pipeline for market data ingestion - Visualization of returns and key metrics - Parameter sensitivity analysis Use pandas, numpy, and scipy. Include realistic assumptions about market microstructure.
© Seth Hobson · MIT · wshobson/agents