Modular Code

This teaches Claude to organize Python code into maintainable modules, with a practical heuristic that 150-500 lines is the sweet spot for both human comprehension and AI context windows. It's opinionated about when to split (anything over 1000 lines is too large, 2000+ causes real tooling problems) and gives concrete patterns like splitting by domain concept or I/O boundary. The guidance is sensible but not dogmatic. It acknowledges that some domain-specific modules like scipy internals might reasonably exceed these limits, and warns against over-modularizing into "package hell." Useful if you're working on a codebase that's grown organically and you need clear criteria for when refactoring is worth the effort.

skills.sh installs: 567
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill modular-code --agent claude-code

Installs into .claude/skills of the current project.

Files

Modular Code Organization

Write modular Python code with files sized for maintainability and AI-assisted development.

File Size Guidelines

Lines	Status	Action
150-500	Optimal	Sweet spot for AI code editors and human comprehension
500-1000	Large	Look for natural split points
1000-2000	Too large	Refactor into focused modules
2000+	Critical	Must split - causes tooling issues and cognitive overload

When to Split

Split when ANY of these apply:

File exceeds 500 lines
Multiple unrelated concerns in same file
Scroll fatigue finding functions
Tests for the file are hard to organize
AI tools truncate or miss context

How to Split

Natural Split Points

By domain concept: auth.py → auth/login.py, auth/tokens.py, auth/permissions.py
By abstraction layer: Separate interface from implementation
By data type: Group operations on related data structures
By I/O boundary: Isolate database, API, file operations