@unisone/claude-toolkit
v1.0.0
Published
Professional AI coding toolkit — techdebt scanner + git worktree parallelization. Works with Claude Code, Cursor, Codex, or any AI coding tool.
Maintainers
Readme
Claude Toolkit
Professional AI coding toolkit — techdebt scanner + git worktree parallelization
Two essential tools that supercharge AI-powered development workflows. Works with Claude Code, Cursor, Codex, or any AI coding assistant.
Features
🔍 Techdebt Scanner
Automated code quality detection that finds:
- 📋 Duplicated code patterns
- 💀 Dead/unreachable code
- 📝 TODO/FIXME/HACK markers
- 🔒 Type safety gaps (TypeScript)
- 📦 Dependency hygiene
- 📏 File size violations
Perfect for: End-of-session cleanup, PR reviews, CI/CD quality gates
🌳 Git Worktree Manager
Create parallel development environments without branch-switching chaos:
- 🚀 Isolated contexts for multi-tasking
- 🤖 Perfect for parallel AI agents
- 🔄 No rebuild thrashing
- 🧠 Preserve mental context
Perfect for: Multi-agent workflows, parallel features, bug fixes while developing
Quick Start
Install
# Run directly with npx (no install)
npx @unisone/claude-toolkit techdebt
# Or install globally
npm install -g @unisone/claude-toolkit
# Or clone and use directly
git clone https://github.com/unisone/claude-toolkit
cd claude-toolkit
npm linkUsage
Techdebt Scanner
# Scan current directory
techdebt
# Scan specific project
techdebt /path/to/project
# Auto-fix safe issues (unused imports, formatting)
techdebt --fix
# Summary only
techdebt --summary
# Generate markdown report
npx @unisone/claude-toolkit techdebt > techdebt-report.mdExample output:
CRITICAL (must fix before merge)
---------------------------------
[FILE_SIZE] src/Dashboard.tsx (547 lines)
→ Split into smaller components
[DUPLICATE] src/utils/validator.ts:45-67
→ Extract to shared utility
HIGH (fix this sprint)
----------------------
[TYPE_GAP] src/models/user.ts:34
Function missing return type
→ Add explicit return type
SUMMARY
-------
Critical: 2
High: 3
Medium: 7
Low: 4
Total: 16 issuesWorktree Manager
# Create parallel worktrees
worktrees /path/to/repo
# Custom worktree names
worktrees /path/to/repo backend frontend testing
# Creates structure:
# repo/ # Main (read-only)
# repo-backend/ # Worktree 1
# repo-frontend/ # Worktree 2
# repo-testing/ # Worktree 3Then navigate with shell aliases:
alias za='cd ~/Projects/repo-backend'
alias zb='cd ~/Projects/repo-frontend'
alias zc='cd ~/Projects/repo-testing'
# Jump between worktrees instantly
za # → backend work
zb # → frontend work (in parallel!)Cleanup when done:
# Scripts also available directly
./scripts/worktrees/teardown-worktrees.sh /path/to/repoClaude Code Integration
1. Install the Techdebt Skill
Drop the skill into your Claude workspace:
# Copy SKILL.md to your .claude/skills/ directory
cp skills/techdebt/SKILL.md ~/.claude/skills/techdebt.md
# Or create a symlink for auto-updates
ln -s $(pwd)/skills/techdebt/SKILL.md ~/.claude/skills/techdebt.mdNow Claude can run techdebt scans automatically at the end of coding sessions!
2. Multi-Agent Worktree Pattern
Use worktrees to run multiple Claude agents in parallel without conflicts:
# Setup parallel worktrees
worktrees ~/Projects/my-app agent-refactor agent-tests agent-docs
# Spawn sub-agents, each in their own worktree
claude spawn --label refactor --workdir ~/Projects/my-app-agent-refactor
claude spawn --label tests --workdir ~/Projects/my-app-agent-tests
claude spawn --label docs --workdir ~/Projects/my-app-agent-docsEach agent works in isolation. No file conflicts. Clean merges.
Configuration
Techdebt Scanner
Create .techdebt.json in your project root:
{
"fileSize": {
"warning": 300,
"critical": 500
},
"functionSize": {
"warning": 50,
"critical": 100
},
"duplicateThreshold": 10,
"excludePaths": [
"node_modules",
"dist",
"build"
],
"autoFix": {
"unusedImports": true,
"formatting": false
}
}CI/CD Integration
GitHub Actions:
name: Code Quality
on: [pull_request]
jobs:
techdebt:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- run: npx @unisone/claude-toolkit techdebtPre-commit hook:
#!/bin/bash
# .git/hooks/pre-commit
npx @unisone/claude-toolkit techdebt --summaryWhy This Toolkit?
The AI Coding Velocity Problem
AI assistants ship fast. Quality control can't keep up.
When you have Claude, Cursor, or Codex generating thousands of lines per session:
- Technical debt accumulates faster than humans can review
- Parallel agents create branch chaos (Agent A conflicts with Agent B)
- Context switching kills productivity (branch checkout = rebuild = 5min lost)
- Type safety erodes (
anytypes slip through,@ts-ignoreproliferates) - Dead code piles up (commented blocks, failed experiments)
This toolkit solves both problems: automated quality checks + conflict-free parallelization.
The Parallel Agents Trend
Worktrees are becoming the standard for AI-native development:
- Codex macOS app — Uses worktrees for multi-agent orchestration
- AirOps — Built
worktree-clifor parallel agent workflows - Medium articles — Growing coverage of worktree patterns for AI coding
- Boris Cherny (2019) — Pioneered parallel worktree development
Why now? AI agents made parallelization essential. Traditional branch-switching workflows break when you have:
- 3 agents refactoring different modules simultaneously
- Production hotfix needed while feature branch is mid-build
- Experimental refactor running alongside stable development
Git worktrees solve this. This toolkit makes them trivial to use.
Comparison: Techdebt Scanner vs Alternatives
| Feature | claude-toolkit | SonarQube | ESLint | GitHub Advanced Security |
|---------|----------------|-----------|--------|--------------------------|
| Zero config | ✅ Works out of box | ❌ Complex setup | ⚠️ Needs config | ❌ Enterprise only |
| Lightweight | ✅ Bash script | ❌ Java server | ✅ Node package | ❌ Cloud service |
| AI-workflow native | ✅ Built for AI coding | ❌ Traditional CI/CD | ⚠️ General purpose | ❌ Security focus |
| Duplicate detection | ✅ --duplicates flag | ✅ Advanced | ❌ Separate tool | ❌ Not included |
| File size limits | ✅ Built-in | ⚠️ Via custom rules | ❌ Manual | ❌ Not applicable |
| Dead code detection | ✅ Commented blocks | ✅ Advanced | ⚠️ Limited | ❌ Not included |
| Type safety gaps | ✅ TypeScript focused | ✅ Multi-language | ⚠️ Linting only | ❌ Not included |
| Dependency audit | ✅ npm audit integration | ✅ Advanced | ❌ Separate tool | ✅ Dependabot |
| JSON output for CI | ✅ --json flag | ✅ REST API | ⚠️ Custom formatter | ✅ API |
| Threshold filtering | ✅ --threshold flag | ✅ Quality gates | ❌ Manual | ⚠️ Custom rules |
| Auto-fix | ✅ --fix flag | ⚠️ Limited | ✅ --fix flag | ❌ Manual |
| Cost | ✅ Free (MIT) | ⚠️ Free tier limited | ✅ Free (MIT) | ❌ Paid enterprise |
When to use what:
- claude-toolkit — Daily AI coding workflows, fast feedback, zero setup
- SonarQube — Enterprise CI/CD, compliance requirements, multi-repo dashboards
- ESLint — JavaScript/TypeScript linting, strict style enforcement
- GitHub Advanced Security — Security vulnerability scanning, enterprise compliance
Combine them! Use claude-toolkit for fast local checks, ESLint for style, SonarQube for team dashboards.
Real-World Use Cases
- Post-session cleanup — Run
techdebt --fixafter Claude builds features - Parallel bug fixing — Fix prod issues in worktree B while building in worktree A
- Multi-agent refactoring — Spawn 3 agents in 3 worktrees, merge when done
- PR quality gates — Fail CI if critical techdebt detected
- Code archaeology — Use analysis worktree for safe exploration
- A/B implementation testing — Try two approaches in parallel worktrees, keep the best
Documentation
- Techdebt Scanner:
skills/techdebt/SKILL.md - Worktree Manager:
scripts/worktrees/README.md - CLI Help: Run
techdebt --helporworktrees --help
Requirements
- Node.js: >=18
- Git: 2.20+ (for worktrees)
- Bash: 4.0+ (macOS/Linux)
Optional (enhanced features):
eslint— Auto-fix linting issuesprettier— Auto-format codejq— JSON parsing for advanced features
Contributing
Contributions welcome! This is a community-driven toolkit.
See CONTRIBUTING.md for:
- Development workflow
- Conventional commit guidelines
- Testing procedures
- High-priority contribution areas
Quick start:
# Fork and clone
git clone https://github.com/YOUR-USERNAME/claude-toolkit
cd claude-toolkit
# Make changes
git checkout -b feat/my-feature
# Test using dogfooding!
./skills/techdebt/scripts/scan.sh
./skills/techdebt/scripts/scan.sh --fix
# Commit and PR
git commit -m "feat: add Python support"
git push origin feat/my-featureDocumentation
- README.md — Main documentation (this file)
- CONTRIBUTING.md — Contribution guidelines
- CHANGELOG.md — Release history
- examples/ — Usage examples and patterns
- Skills:
License
MIT © Alex Zay
See LICENSE for full text.
Built for the AI coding era. Maintained by humans (for now).
Questions? Open an issue or find me on X/Twitter.
