Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/quantweb3-com/nexustrader/claude-mdgit clone --depth 1 https://github.com/Quantweb3-com/NexusTraderWhat 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 | $0.01552 | $0.01552 |
| Opus 5 | $0.00776 | $0.00776 |
| Sonnet 5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
NexusTrader 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
NexusTrader is a professional-grade quantitative trading platform built with Python 3.11+ that focuses on high-performance, low-latency trading across multiple exchanges. It features a modular, event-driven architecture with Rust-powered core components for maximum performance.
Development Commands
Dependencies and Setup
# Install with uv (package manager used in this project)
uv sync
# Install development dependencies
uv sync --group dev
# Install pre-commit hooks (required for contributions)
uv add --dev pre-commit
pre-commit install
Testing
# Run all tests with async support
uv run pytest
# Run specific test modules
uv run pytest test/core/
uv run pytest test/core/test_entity.py
# Test configuration: pytest.ini enables asyncio_mode = auto
Code Quality
# Linting and formatting (via ruff)
uv run ruff check
uv run ruff format
Development Infrastructure
# Start Redis, PostgreSQL, Loki logging stack
docker-compose up -d
# Clear log files
./clear.sh
# Process management (production)
pm2 start ecosystem.config.js
Architecture Overview
Core Components
- Engine: Central orchestrator managing all trading systems (
nexustrader/engine.py) - Strategy: Base class for trading logic with multiple execution modes (
nexustrader/strategy.py) - Connectors: Exchange-specific public (market data) and private (trading) connectors
- EMS (Execution Management System): Order submission and execution
- OMS (Order Management System): Order state tracking and management
- Cache: High-performance data caching layer (
nexustrader/core/cache.py) - Registry: Order and component tracking (
nexustrader/core/registry.py)
Exchange Integration
Each exchange follows a consistent pattern in nexustrader/exchange/{exchange}/:
- PublicConnector: Market data WebSocket streams
- PrivateConnector: Account data and order execution
- EMS/OMS: Exchange-specific order management
- ExchangeManager: Coordinate connectors and systems
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.
- 3d ago First seen · 211 lines · 1,552 tokens per session scan A 693cc9ad4132
NexusTrader CLAUDE.md is an instructions file published in the GitHub repository Quantweb3-com/NexusTrader (658 stars, last pushed 3mo ago), licensed MIT. It adds 1,552 tokens to every session, about $0.0078 per session on Opus 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.
Other instructions, from other repositories
uv AGENTS.md
AGENTS.md instructions for astral-sh/uv, a project described as: An extremely fast Python package and project manager, written in Rust.
binance-net
Use Binance.Net when generating C#/.NET code that interacts with the Binance cryptocurrency exchange — including Spot, Margin, USD-M Futures, COIN-M Futures, Options, sub-accounts, brokerage, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on any request…
xalpha AGENTS.md
Instructions for refraction-ray/xalpha, covering xalpha agent platform guidelines, 1. the agentic workflow, 2. core compatibility contracts, 3. data scraping & api resilience and 4. local caching.
tradememory-protocol AGENTS.md
Instructions for mnemox-ai/tradememory-protocol, covering tradememory protocol — agent context, project rules, recent changes and current status.
kraken-net
Use Kraken.Net when generating C#/.NET code that interacts with the Kraken cryptocurrency exchange, including Spot REST, Spot WebSocket v2, Futures REST, Futures WebSocket, account data, market data, order placement, Kraken Earn, local order books, dependency injection, or CryptoExchange.Net SharedApis. Triggers on…
kucoin-net
Use Kucoin.Net when generating C#/.NET code that interacts with the Kucoin cryptocurrency exchange API, including Spot, Margin, High Frequency spot trading, Futures, Unified Account, REST endpoints, WebSocket subscriptions, account management, market data, or order placement. Triggers on any request mentioning Kucoin…