@aicompanyusa/codebase-optimizer
v1.0.0
Published
AI-driven codebase analysis framework for Claude Code
Maintainers
Readme
Codebase Optimizer
Systematic AI-driven codebase analysis and refactoring framework for Claude Code.
Achieves 5-11% improvement in code understanding and recommendation quality through repository-specific context engineering.
Quick Start
One-Command Install (Recommended)
# Install agents and tools to your system
npx github:TaylorHonaker/codebase-optimizer init
# Full install (agents + template + config + pre-commit hook)
npx github:TaylorHonaker/codebase-optimizer init --all
# Run analysis on your project
claude "Run codebase-optimizer on src/"Manual Install (Alternative)
# 1. Clone the repo
git clone https://github.com/TaylorHonaker/codebase-optimizer.git
cd codebase-optimizer
# 2. Run install script
./scripts/install.sh --all
# 3. Run analysis
claude "Run codebase-optimizer on src/"One-Liner (Full Analysis)
Run this from any repository root for a complete analysis with Best-of-N candidate solutions:
claude --dangerously-skip-permissions -p "Run codebase-optimizer on the entire repository. Generate a full analysis report with Best-of-N candidates for any issues found."Shell Alias (Optional)
Add to your ~/.bashrc or ~/.zshrc:
alias optimize='claude --dangerously-skip-permissions -p "Run codebase-optimizer on the entire repository. Generate a full analysis report with Best-of-N candidates for any issues found."'Activate and use:
source ~/.bashrc
cd ~/projects/some-repo
optimizeRequirements
- Claude Code CLI: Install from npm
- Anthropic API Key: Set
ANTHROPIC_API_KEYenvironment variable
Platform Support
| Platform | Support | Notes |
|----------|---------|-------|
| macOS | Native | All scripts work directly |
| Linux | Native | All scripts work directly |
| Windows | Via WSL/Git Bash | See Windows Setup Guide below |
| Docker | Full | Use bootstrap/docker-compose.yml for sandboxed execution |
Windows Setup Guide
Shell scripts require a Unix-like environment on Windows. Choose one of these options:
Option 1: Git Bash (Recommended)
The easiest option - included with Git for Windows.
Install Git for Windows: https://git-scm.com/downloads
- During installation, select "Git Bash Here" context menu option
- Select "Use Git from Git Bash only" (safer) or "Use Git from Windows Command Prompt"
Open Git Bash and verify:
bash --version # Should show 4.x or higher git --version # Verify Git worksRun scripts normally:
cd /c/path/to/codebase-optimizer ./scripts/install.sh
Option 2: WSL2 (Best Performance)
For heavy usage, WSL2 provides a full Linux environment.
Install WSL2 (run in PowerShell as Administrator):
wsl --installRestart your computer when prompted
Install Ubuntu from Microsoft Store (or use default)
Clone repo in WSL filesystem (better performance):
cd ~ git clone https://github.com/ai-company-usa/codebase-optimizer.git cd codebase-optimizer ./scripts/install.sh
Tip: Store repos in WSL filesystem (
/home/user/) not Windows filesystem (/mnt/c/) for 10x better I/O performance.
Option 3: Docker (Sandboxed)
Best for automation and isolated execution.
cd bootstrap
docker-compose upSee bootstrap/docker-compose.yml for configuration options.
Common Windows Issues
Issue: ./script.sh: Permission denied
# Fix: Make scripts executable
chmod +x scripts/*.shIssue: $'\r': command not found (line ending errors)
# Fix: Configure Git to use Unix line endings
git config --global core.autocrlf input
# For existing files, convert them:
sed -i 's/\r$//' scripts/*.shIssue: claude: command not found
# Fix: Ensure npm global bin is in PATH
# Add to ~/.bashrc:
export PATH="$PATH:$(npm config get prefix)/bin"
source ~/.bashrcIssue: Scripts work in Git Bash but not PowerShell
# PowerShell cannot run .sh files directly
# Always use Git Bash or WSL for shell scriptsWhat This Does
| Component | Purpose | Impact |
|-----------|---------|--------|
| CLAUDE.md | Repository-specific context | +5-11% understanding |
| Custom Subagents | Specialized analysis tasks | Consistent methodology |
| Automation Scripts | Scheduled audits | Zero-maintenance hygiene |
| Best-of-N Framework | Multiple solution candidates | Higher quality recommendations |
Repository Structure
codebase-optimizer/
├── bin/ # CLI entry point (npx support)
│ └── cli.js # Main executable
├── templates/ # CLAUDE.md templates by stack
│ ├── CLAUDE.md.template # Base template (start here)
│ ├── CLAUDE-nodejs.md # Node.js/JavaScript
│ ├── CLAUDE-python.md # Python
│ ├── CLAUDE-ghl.md # GoHighLevel + n8n stack
│ └── CLAUDE-remotion.md # Video pipeline
├── agents/ # Claude Code custom subagents
│ ├── codebase-optimizer.md
│ ├── dependency-auditor.md
│ ├── security-scanner.md
│ └── performance-profiler.md
├── scripts/ # Automation
│ ├── install.sh # Setup script
│ ├── weekly-audit.sh # Scheduled analysis
│ ├── pre-commit-check.sh # Git hook
│ └── generate-report.sh # Markdown report generator
├── docs/ # Methodology documentation
│ └── METHODOLOGY.md # Full framework explanation
├── examples/ # Sample outputs
│ └── audit-report-sample.md
└── package.json # npm package (enables npx install)Templates
Base Template
Copy templates/CLAUDE.md.template to your repo root and customize.
Stack-Specific Templates
- Node.js:
CLAUDE-nodejs.md- Express, React, async patterns - Python:
CLAUDE-python.md- FastAPI, async, type hints - GoHighLevel:
CLAUDE-ghl.md- GHL API, n8n, Airtable integration - Remotion:
CLAUDE-remotion.md- Video pipeline, audio sync
Custom Agents
Install agents to ~/.claude/agents/:
./scripts/install.shAvailable Agents
| Agent | Invocation | Purpose |
|-------|------------|---------|
| codebase-optimizer | Full analysis | Comprehensive refactoring roadmap |
| dependency-auditor | Dependency check | Outdated/vulnerable packages |
| security-scanner | Security audit | Vulnerabilities, secrets, access |
| performance-profiler | Performance | Bottlenecks, algorithmic issues |
Usage
# Full analysis
claude "Run codebase-optimizer on src/"
# Dependency audit only
claude "Run dependency-auditor"
# Security scan
claude "Run security-scanner on auth/ and api/"
# Performance profiling
claude "Run performance-profiler on lib/database/"Automation
Weekly Audit (Recommended)
# Add to crontab (runs Sunday 2 AM)
0 2 * * 0 /path/to/codebase-optimizer/scripts/weekly-audit.sh /path/to/repoOr Windows Task Scheduler:
.\scripts\Register-WeeklyAudit.ps1 -RepoPath "C:\repos\your-project"Pre-Commit Hook
# Install hook
cp scripts/pre-commit-check.sh /path/to/repo/.git/hooks/pre-commit
chmod +x /path/to/repo/.git/hooks/pre-commitCatches:
- Functions >100 lines
- Duplicate code blocks
- Hardcoded secrets patterns
- TODO/FIXME older than 30 days
Methodology
Best-of-N Iterative Analysis
For each identified issue:
- Generate 3-5 candidate solutions
- Score each candidate:
- Performance Impact (40%)
- Maintainability (30%)
- Implementation Complexity (-20%)
- Risk Level (-10%)
- Recommend highest-scoring option
- Include alternatives with tradeoffs
Priority Tiers
| Tier | Criteria | Action Timeline | |------|----------|-----------------| | CRITICAL | Security vulnerabilities, >100ms latency, breaking architecture | Immediate | | HIGH | 30%+ performance gain, important updates, structural improvements | This sprint | | MEDIUM | Code quality, minor optimizations, tech debt | This quarter | | LOW | Cosmetic, future-proofing, edge cases | Backlog |
Feedback Loop
After implementing recommendations:
claude "Implemented [recommendation]. Before: [X]. After: [Y]. Calibrate future recommendations."This trains the system to your codebase patterns.
Integration
CI/CD
# .github/workflows/code-quality.yml
name: Code Quality Check
on: [pull_request]
jobs:
analyze:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Quick Analysis
run: |
claude -p "Check for code smells in changed files:
- Functions >100 lines
- Duplicate code
- Missing error handling
Output as PR comment format." --max-turns 3NotebookLM
Upload weekly audit reports to a "Codebase Health" notebook for:
- Audio overview during commute
- Trend analysis across audits
- Team knowledge sharing
Configuration
Environment Variables
# Optional: Override default settings
export CODEBASE_OPTIMIZER_MAX_ITERATIONS=50
export CODEBASE_OPTIMIZER_OUTPUT_DIR=./docs/audits
export CODEBASE_OPTIMIZER_NOTIFY_SLACK=https://hooks.slack.com/...Settings File
Create .codebase-optimizer.json in repo root:
{
"exclude": ["node_modules", "dist", "coverage", ".git"],
"focus": ["src", "lib", "api"],
"severity_threshold": "MEDIUM",
"max_file_size_kb": 500,
"custom_rules": {
"max_function_lines": 100,
"max_file_lines": 500,
"require_error_handling": true
}
}License
MIT - AI Company USA
Contributing
For client deployments, customize templates per engagement.
"Fix reliability before automation. Achieve 100% success rate manually first, then schedule."
