🤖 BTST Trading Research Agents: a multi-agent AI system for overnight stock research.

I designed four specialised AI subagents and packaged them as a Claude Code / Cowork plugin. They automate the research for BTST (buy today, sell tomorrow) trades in NSE F&O stocks.

The agents: 🌍 market-context: decides if it’s safe to hold new positions overnight (index moves, VIX, FII/DII flows, global cues, upcoming events). 📰 catalyst-analyst: finds out why each stock moved, scores its news catalyst from -2 to +2, and vetoes stocks with real event risk. ☀️ morning-briefer: an 8:30 AM pre-market brief with a buy/sell watchlist and a table showing which data was verified. 🎯 exit-manager: reads live holdings and prices through a read-only Zerodha Kite MCP connection and recommends sell or hold for each position.

Design highlights: • Each agent gets only the tools it needs, and none of them can place orders. • Agents return structured JSON so the next step in the workflow can use their output directly. • Scheduled tasks run the full trading day automatically (8:30 AM, 3:05 PM, 4:15 PM). • Built-in honesty: if a fact can’t be verified, the agent leaves it out or marks it “NOT verified” instead of making it up.

Tech: Claude Code subagents · MCP · Prompt engineering · Plugin packaging 🔗 github.com/bns218/BTST