agent-trading-arena: Instructions file for Claude Code

CLAUDE.md

agent-trading-arena CLAUDE.md is an instructions file for Claude Code from 0xhubed/agent-trading-arena. It costs 9,768 tokens per session, scanned A, original, MIT.

A cryptocurrency futures trading simulator where AI agents compete using live Kraken Futures data. It supports command-line runs, configuration files, an API dashboard, a React frontend, optional learning tools, and historical data management.

In plain words
What is it for?
Use it to run trading simulations, create configuration templates, start the API or frontend, manage historical data, lint the Python code, and run tests.
Why use it?
It provides a documented way to install the simulator, run competitions or demos, check code, and work with its data and dashboard.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is 0xhubed/agent-trading-arena's own configuration. It tells Claude Code how to work on agent-trading-arena itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-trading-arena configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0xhubed/agent-trading-arena. 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/0xhubed/agent-trading-arena/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/0xhubed/agent-trading-arena

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.

agentmods badge for agent-trading-arena CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xhubed/agent-trading-arena/claude-md/github.svg)](https://agentmods.dev/instructions/0xhubed/agent-trading-arena/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/0xhubed/agent-trading-arena/claude-md"><img src="https://agentmods.dev/badge/instructions/0xhubed/agent-trading-arena/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.

agentmods 80×15 button for agent-trading-arena CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/0xhubed/agent-trading-arena/claude-md"><img src="https://agentmods.dev/badge/instructions/0xhubed/agent-trading-arena/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,768 This file is loaded in full into every session.
When invoked 9,768 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.09768 $0.09768
Opus 5 $0.04884 $0.04884
Sonnet 5 $0.01954 $0.01954
Haiku 4.5 $0.00977 $0.00977

Measured 9d ago against content hash a831c963ab05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-trading-arena CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Database at `data/arena.db`. Reset with: `rm data/arena.db` or `curl -X POST http://localhost:8000/api/reset`
CLAUDE.md · 773 lines

How it starts

The opening of the file, as written. The whole thing — 773 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

Agent Arena is an AI-powered cryptocurrency futures trading simulation where LLM-based agents compete using real Kraken Futures market data. Agents make trading decisions on crypto futures (BTC, ETH, SOL, XRP, DOGE) and compete on a profitability leaderboard.

Commands

# Install in development mode (core + dev + api)
pip install -e ".[dev,api]"

# Optional extras
pip install -e ".[learning]"   # Postgres + pgvector + OpenAI embeddings

# Run single-tick demo (CLI)
agent-arena demo

# Run competition from config file (CLI)
agent-arena run configs/production.yaml
agent-arena run configs/local_inference.yaml  # Local/Together AI models

# Create new config template
agent-arena init

# Run API server with dashboard
uvicorn agent_arena.api.app:app --reload --port 8000

# Run React frontend (in separate terminal)
cd frontend && npm install && npm run dev

# Lint
ruff check agent_arena/

# Run tests
pytest
pytest tests/test_specific.py -k "test_name"  # single test

# Historical data management
agent-arena data-status                           # Show available data
agent-arena fetch-data -S 2025-01-01 -s PF_XBTUSD # Fetch from Kraken Futures

# Contagion analysis
agent-arena contagion analyze           # System health / echo chamber risk
agent-arena contagion history           # Contagion history

# Scenario management
agent-arena scenario curate             # Curate Kraken Futures data as replayable scenarios
agent-arena scenario list               # List saved scenarios
agent-arena scenario verify             # Verify scenario integrity

# Codegen (journal-driven code fixes)
agent-arena codegen --dry-run                    # Show findings only
agent-arena codegen --max-changes 1 --no-pr      # One fix, no PR
agent-arena codegen                              # Full: branch + edits + PR
agent-arena codegen --lookback-days 10           # Scan more journal entries

Read the full file on GitHub · 773 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.

  1. 9d ago First seen · 773 lines · 9,768 tokens per session scan A a831c963ab05

Subscribe to this mod's changes

agent-trading-arena CLAUDE.md is an instructions file published in the GitHub repository 0xhubed/agent-trading-arena (8 stars, last pushed 4mo ago), licensed MIT. It adds 9,768 tokens to every session, about $0.0488 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens