This directory contains the complete analysis of your Python project generated by code2llm. Each file serves a specific purpose for understanding, refactoring, and documenting your codebase.
When you run code2llm ./ -f all, the following files are created:
| File | Format | Purpose | Key Insights |
|---|---|---|---|
analysis.toon |
TOON | 🔥 Health diagnostics - Complexity, god modules, coupling | 52 critical functions, 0 god modules |
project.toon |
TOON | 🧠 Project logic - Compact module view from code2logic | Generated via code2logic integration |
| File | Format | Purpose | Use Case |
|---|---|---|---|
context.md |
Markdown | 📖 LLM narrative - Architecture summary | Paste into ChatGPT/Claude for code analysis |
# Quick health check (TOON format only)
code2llm ./ -f toon
# Generate all formats (what created these files)
code2llm ./ -f all
# LLM-ready context only
code2llm ./ -f context# Fast analysis for large projects
code2llm ./ -f toon --strategy quick
# Memory-limited analysis
code2llm ./ -f all --max-memory 500
# Skip PNG generation (faster)
code2llm ./ -f all --no-png# Get refactoring recommendations
code2llm ./ -f evolution
# Focus on specific code smells
code2llm ./ -f toon --refactor --smell god_function
# Data flow analysis
code2llm ./ -f flow --data-flowPurpose: Quick overview of code health issues Key sections:
- HEALTH: Critical issues (🔴) and warnings (🟡)
- REFACTOR: Prioritized refactoring actions
- COUPLING: Module dependencies and potential cycles
- LAYERS: Package complexity metrics
- FUNCTIONS: High-complexity functions (CC ≥ 10)
- CLASSES: Complex classes needing attention
Example usage:
# View health issues
cat analysis.toon | head -30
# Check refactoring priorities
grep "REFACTOR" analysis.toonPurpose: Step-by-step refactoring plan Key sections:
- NEXT: Immediate actions to take
- RISKS: Potential breaking changes
- METRICS-TARGET: Success criteria
Example usage:
# Get refactoring plan
cat evolution.toon
# Track progress
grep "NEXT" evolution.toonPurpose: Understand data movement through the system Key sections:
- PIPELINES: Data processing chains
- CONTRACTS: Function input/output contracts
- SIDE_EFFECTS: Functions with external impacts
Example usage:
# Find data pipelines
grep "PIPELINES" flow.toon
# Identify side effects
grep "SIDE_EFFECTS" flow.toonPurpose: High-level architecture overview Key sections:
- MODULES: All modules with basic stats
- IMPORTS: Dependency relationships
- SIGNATURES: Public API functions
Example usage:
# See project structure
cat map.toon | head -50
# Find public APIs
grep "SIGNATURES" map.toonPurpose: Compact module view generated by code2logic integration Key sections:
- Modules list: All project modules with file sizes
- Imports: Dependency information
- Classes/Functions: Summary counts
When to use: When you need a lightweight project overview combined with code2llm analysis
Example usage:
# View compact project structure
cat project.toon | head -30
# Find largest files
grep -E "^ .*[0-9]{3,}$" project.toon | sort -t',' -k2 -n -r | head -10Purpose: Pre-formatted prompt listing all generated files for LLM conversation Contents:
- Files section: Lists all existing generated files with descriptions
- Missing section: Shows which files weren't generated (if any)
- Task section: Instructions for LLM analysis
- Requirements section: Guidelines for suggested changes
Example usage:
# View the prompt
cat prompt.txt
# Copy to clipboard and paste into ChatGPT/Claude
cat prompt.txt | pbcopy # macOS
cat prompt.txt | xclip -sel clip # LinuxPurpose: Ready-to-paste context for AI assistants Key sections:
- Overview: Project statistics
- Architecture: Module breakdown
- Entry Points: Public interfaces
- Patterns: Design patterns detected
Example usage:
# Copy to clipboard for LLM
cat context.md | pbcopy # macOS
cat context.md | xclip -sel clip # Linux
# Use with Claude/ChatGPT for code analysisPurpose: Visual understanding of code structure Files:
flow.mmd- Detailed control flow with complexity colorscalls.mmd- Simple call graphcompact_flow.mmd- High-level module view*.png- Pre-rendered images
Example usage:
# View diagrams
open flow.png # macOS
xdg-open flow.png # Linux
# Edit in Mermaid Live Editor
# Copy content of .mmd files to https://mermaid.live# Quick health check
code2llm ./ -f toon
cat analysis.toon | grep -E "(HEALTH|REFACTOR)"# Get refactoring queue
code2llm ./ -f evolution
cat evolution.toon
# Focus on specific issues
code2llm ./ -f toon --refactor --smell god_function# Generate context for AI
code2llm ./ -f context
cat context.md
# Use with Claude: "Based on this context, help me refactor the god modules"# Generate all docs for team
code2llm ./ -f all -o ./docs/
# Create visual diagrams
open docs/flow.png- 🔴 Critical (≥5.0): Immediate refactoring needed
- 🟠 High (3.0-4.9): Consider refactoring
- 🟡 Medium (1.5-2.9): Monitor complexity
- 🟢 Low (0.1-1.4): Acceptable
- ⚪ Basic (0.0): Simple functions
- GOD Module: Too large (>500 lines, >20 methods)
- HUB: High fan-out (calls many modules)
- FAN-IN: High incoming dependencies
- CYCLES: Circular dependencies
- PIPELINE: Sequential data processing
- CONTRACT: Clear input/output specification
- SIDE_EFFECT: External state modification
#!/bin/bash
# Analyze code quality in CI
code2llm ./ -f toon -o ./analysis
if grep -q "🔴 GOD" ./analysis/analysis.toon; then
echo "❌ God modules detected"
exit 1
fi#!/bin/sh
# .git/hooks/pre-commit
code2llm ./ -f toon -o ./temp_analysis
if grep -q "🔴" ./temp_analysis/analysis.toon; then
echo "⚠️ Critical issues found. Review before committing."
fi
rm -rf ./temp_analysis# Generate docs for README
code2llm ./ -f context -o ./docs/
echo "## Architecture" >> README.md
cat docs/context.md >> README.mdFunkcja, która robi zbyt wiele rzeczy naraz i staje się "wszechmocna" w danym module. Jest to antywzorzec w inżynierii oprogramowania (ang. anti-pattern).
Metryka mierząca, jak skomplikowana jest funkcja lub metoda na podstawie liczby możliwych ścieżek wykonania kodu.
Specjalny format plików używany przez code2llm do przechowywania analizy kodu w strukturze YAML.
System automatycznego przełączania między modelami AI (free → local → paid) w celu optymalizacji kosztów i wydajności.
Moduł lub zdolność w systemie CoreSkill, który może być tworzony, naprawiany i ewoluowany automatycznie.
Silnik odpowiedzialny za automatyczną ewolucję i rozwój skillów w systemie CoreSkill.
Wskaźnik problemów w kodzie, który może prowadzić do trudności w utrzymaniu lub rozszerzeniu systemu.
Poziom powiązań i zależności między modułami w systemie.
Metryki zależności modułów: fan-out - liczba modułów wywoływanych, fan-in - liczba modułów wywołujących dany moduł.
Sekwencja kroków przetwarzania danych przepływających przez system.
Efekt uboczny funkcji - zmiana stanu systemu poza jej bezpośrednim zakresem.
Kontrakt wejścia/wyjścia funkcji - określa oczekiwane parametry i zwracane wartości.
- Review
analysis.toon- Identify critical issues - Check
evolution.toon- Plan refactoring priorities - Use
context.md- Get LLM assistance for complex changes - Reference visualizations - Understand system architecture
- Track progress - Re-run analysis after changes
# Deep analysis with all insights
code2llm ./ -m hybrid -f all --max-depth 15 -v
# Performance-optimized
code2llm ./ -m static -f toon --strategy quick
# Refactoring-focused
code2llm ./ -f toon,evolution --refactor# Separate output directories
code2llm ./ -f all -o ./analysis-$(date +%Y%m%d)
# Split YAML into multiple files
code2llm ./ -f yaml --split-output
# Separate orphaned functions
code2llm ./ -f yaml --separate-orphansGenerated by: code2llm ./ -f all --readme
Analysis Date: 2026-03-05
Total Functions: 820
Total Classes: 104
Modules: 102
For more information about code2llm, visit: https://github.com/tom-sapletta/code2llm
Apache License 2.0 - see LICENSE for details.
Created by Tom Sapletta - tom@sapletta.com