What is indian-trading-agent CLAUDE.md?

Project instructions for an AI-assisted trading system for Indian markets, meaning the NSE and BSE exchanges. It describes a web interface, a backend, market data and news sources, and multiple cooperating agents; a multi-agent system splits work among several specialized AI components.

Installing dependencies, configuring an Anthropic API key, starting the FastAPI backend and Next.js frontend, and understanding the project’s trading workflow.

They give a coding agent the project’s setup steps, configuration options, architecture, and daily workflow so it can work within the project’s intended structure.

How pradeepsiddappa/indian-trading-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pradeepsiddappa/indian-trading-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pradeepsiddappa/indian-trading-agent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pradeepsiddappa/indian-trading-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pradeepsiddappa/indian-trading-agent/claude-md/github.svg)](https://agentmods.dev/instructions/pradeepsiddappa/indian-trading-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pradeepsiddappa/indian-trading-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/pradeepsiddappa/indian-trading-agent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pradeepsiddappa/indian-trading-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/pradeepsiddappa/indian-trading-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,909 This file is loaded in full into every session.

When invoked 9,909 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.09909	$0.09909
Opus 5.5	$0.03964	$0.03964
Sonnet 5.5	$0.01982	$0.01982
Haiku 4.5	$0.00991	$0.00991

Measured 1mo ago against content hash b5b7083d2be2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

indian-trading-agent CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 576 lines

How it starts

The opening of the file, as written. The whole thing — 576 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Indian Market Trading Agent

AI-powered multi-agent trading decision system for Indian markets (NSE/BSE). Built on TradingAgents framework with LangGraph.

Architecture

frontend/ (Next.js 16 + Tailwind + shadcn/ui + Open Sans)  :3000
    |
backend/ (FastAPI + WebSocket)                             :8000
    |
tradingagents/ (LangGraph multi-agent pipeline)
    |
yfinance + RSS feeds (NSE/BSE data + news)

Quick Start

# 1. Install Python deps
python3 -m venv venv && source venv/bin/activate
pip install -r requirements.txt   # exact, tested versions (Python 3.11+)
pip install -e .

# 2. Configure API keys (2 options)
# Option A: via .env
echo 'ANTHROPIC_API_KEY=your_key' > .env
# Option B: via Settings page in the UI (stored in SQLite, takes priority)

# 3. Start backend
uvicorn backend.app:app --reload --port 8000

# 4. Start frontend (separate terminal)
cd frontend && npm install && npm run dev

# 5. Open http://localhost:3000

Information Architecture

The UI is organized by daily workflow (not by technical feature):

🏠 Today              — Daily starting page with auto-loaded top picks + workflow guide

DISCOVER
  ✨ Top Picks         — AI-free unified recommendation engine (combines all signals)
  📡 Market Scan       — Gap / Volume / Breakout scanner
  🎯 Strategies        — S/R, Pivot Points, Cyclical Patterns (seasonality, sector rotation)
  📰 News Feed         — Aggregated Indian market news (RSS + yfinance, customizable)

ANALYZE
  🔍 Deep Analysis     — AI-powered 10-agent pipeline (paid ~Rs.15-60)
  📊 Charts            — Candlestick charts with volume

VALIDATE
  🏆 Performance       — Historical win rate of each strategy (FREE)
  🧪 Simulation        — Paper trading + historical recommender backtest (FREE)
  🧠 Learning Insights — Pattern analysis of YOUR past trades (FREE, no ML)
  📈 Signal Performance — Per-signal win rate + auto-tune recommender (FREE)
  🎯 Verdict Calibration — Is the daily verdict actually predictive? (FREE)
  ⚖️ Confidence Calibration — Brier score: are stated probabilities honest? (FREE)
  👁️ Shadow Trades       — Counterfactual auto-tracking of skipped picks (FREE)
  🧠 Memory Admin        — Inspect + prune agent BM25 memories (FREE)
  🔬 AI Backtest       — Run AI pipeline on past dates (paid)
  📋 My Trades         — History with P&L tracking + "Teach the agent" reflection

⚙️ Settings           — API keys (UI), LLM provider switcher, model selection, cost guide

Read the full file on GitHub · 576 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +3 lines · +515 tokens per session b5b7083d2be2
2mo ago Changed · +13 lines · +563 tokens per session 8e51bbca7a72
2mo ago First seen · 560 lines · 8,831 tokens per session scan A a42ec1aaebae

Subscribe to this mod's changes

indian-trading-agent CLAUDE.md is an instructions file published in the GitHub repository pradeepsiddappa/indian-trading-agent (32 stars, last pushed 13d ago), licensed Apache-2.0. It adds 9,909 tokens to every session, about $0.0396 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Finance and fintech

indian-trading-agent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
indian-trading-agent CLAUDE.mdpradeepsiddappa/indian-trading-agent	Instructions file	32	13d ago	Apache-2.0	A	9,909	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

indian-trading-agent: Instructions file for Claude Code