baby-smith: Instructions file for Claude Code

CLAUDE.md

baby-smith CLAUDE.md is an instructions file for Claude Code from algo-traders-club/baby-smith. It costs 3,541 tokens per session, scanned A, original, MIT.

A refactoring record for Baby Smith, a trading agent, describing how large files were split into smaller modules and how unused code, error handling, and type information were improved.

In plain words
What is it for?
Use it as project context when maintaining, reviewing, or extending the Baby Smith trading agent.
Why use it?
It explains the structure and goals of a major code cleanup, including what changed from the original design.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is algo-traders-club/baby-smith's own configuration. It tells Claude Code how to work on baby-smith 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 baby-smith configures →

Reuse

Borrowing it

Nothing to install: this file belongs to algo-traders-club/baby-smith. 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/algo-traders-club/baby-smith/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/algo-traders-club/baby-smith

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 baby-smith CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/algo-traders-club/baby-smith/claude-md/github.svg)](https://agentmods.dev/instructions/algo-traders-club/baby-smith/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/algo-traders-club/baby-smith/claude-md"><img src="https://agentmods.dev/badge/instructions/algo-traders-club/baby-smith/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 baby-smith CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/algo-traders-club/baby-smith/claude-md"><img src="https://agentmods.dev/badge/instructions/algo-traders-club/baby-smith/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,541 This file is loaded in full into every session.
When invoked 3,541 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03541 $0.03541
Opus 5.5 $0.01416 $0.01416
Sonnet 5.5 $0.00708 $0.00708
Haiku 4.5 $0.00354 $0.00354

Measured 2mo ago against content hash 537ae67573eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

baby-smith 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 2mo 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 · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Baby Smith Trading Agent - Refactoring Documentation

Overview

This document outlines the comprehensive refactoring performed on the Baby Smith trading agent codebase by Claude Code. The refactoring transformed a monolithic codebase with several large files (1600+ lines) into a well-structured, modular architecture following modern software engineering best practices.

Refactoring Objectives

Primary Goals

  1. File Size Reduction: Break down all files larger than 500 lines into smaller, focused modules
  2. Dead Code Removal: Eliminate unused imports, functions, classes, and variables
  3. Error Handling Enhancement: Implement comprehensive, consistent error handling throughout
  4. Code Quality Improvements: Add type annotations, improve maintainability, and enhance robustness

Before vs After

File Size Comparison

File Before (Lines) After (Lines) Reduction
agent.py 1,651 275 -83%
strategies/market_maker.py 595 13 -98% (modularized)
dashboard.py 687 24 -96% (modularized)
Total Codebase ~4,500+ 4,378 Optimized

Architecture Transformation

Before: Monolithic structure

  • Large, complex files handling multiple responsibilities
  • Inconsistent error handling
  • Missing type annotations
  • Dead/unused code throughout
  • Poor separation of concerns

After: Modular, clean architecture

  • Small, focused modules (all under 500 lines)
  • Comprehensive exception hierarchy
  • Full type annotations
  • Zero dead code
  • Clear separation of concerns

New Architecture

Core Modules (src/agent_smith/core/)

1. trading_engine.py (260 lines)

Purpose: Main orchestration engine that coordinates all trading operations Key Features:

  • Manages the main trading loop with error handling and recovery
  • Coordinates market data, order management, and position tracking
  • Implements graceful shutdown and error recovery mechanisms
  • Provides comprehensive trading state reporting

Read the full file on GitHub · 470 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. 2mo ago First seen · 470 lines · 3,541 tokens per session scan A 537ae67573eb

Subscribe to this mod's changes

baby-smith CLAUDE.md is an instructions file published in the GitHub repository algo-traders-club/baby-smith (11 stars, last pushed 1y ago), licensed MIT. It adds 3,541 tokens to every session, about $0.0142 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.

Related

baby-smith CLAUDE.md compared with instructions from other repositories

baby-smith CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
baby-smith CLAUDE.mdalgo-traders-club/baby-smithInstructions file111y agoMITA3,541Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot