Automatic Quality Gates for Claude Code

Every conversation ends with validation. Linting, formatting, type-checking, and tests run automatically, catching issues before they ship.

How It Works

Quality enforcement that runs automatically, learns from results, and gets faster over time.

One command installs the CLI and auto-detects plugins for your stack.

han plugin install --auto

Claude writes code as usual. No workflow changes needed.

Stop hooks run automatically. Linters, formatters, type checkers, and tests are all verified.

Local metrics track success rates and calibrate confidence. Nothing leaves your machine.

139 plugins across four categories, all working together.

Essential infrastructure. Auto-installs han binary, provides metrics, MCP servers, and quality principles.

Specialized AI agents for code review, debugging, architecture, and security.

Validation plugins for your stack. TypeScript, Biome, Pytest, ShellCheck, and more.

MCP servers connecting Claude to GitHub, Jira, Sentry, and other tools.

⚡

Only runs validation when relevant files change. Native Rust hashing keeps it fast.

📊

Tracks task success and confidence calibration. All data stays on your machine, never sent anywhere.

🔧

Binary auto-installs on first session. --auto flag detects your stack automatically.

🔌

TypeScript, Python, Rust, Go, Ruby, Elixir. If there's a linter, there's a plugin.

Two commands. That's it.

1. Install the CLI:

curl -fsSL https://han.guru/install.sh | bash

2. Auto-detect and install plugins for your project:

han plugin install --auto

That's it. Next time you use Claude Code, validation hooks will run automatically when you finish a conversation.

Built by The Bushido Collective - developers committed to honor, quality, and continuous improvement.

"Beginning is easy - continuing is hard."

- Japanese Proverb

MIT License - Walk the way of Bushido. Practice with Discipline. Build with Honor.