Biome
v1.10.0Comprehensive Biome skills for fast JavaScript/TypeScript linting and formatting with modern tooling and performance optimization.
Installation
Install han binary (required for hooks to work):
curl -fsSL https://han.guru/install.sh | bashThen install this plugin:
han plugin install jutsu-biomeOverview
Comprehensive Biome skills for fast JavaScript/TypeScript linting and formatting with modern tooling and performance optimization.
Skills
This plugin provides the following skills:
- Biome Configuration - Master Biome configuration files, rules, and project setup
- Biome Linting - Expert knowledge of Biome's linting capabilities and rule configuration
- Biome Formatting - Formatting patterns, options, and code style management
Usage
Skills can be invoked using the Skill tool:
Skill("jutsu-biome:biome-configuration")
Skill("jutsu-biome:biome-linting")
Skill("jutsu-biome:biome-formatting")
Each skill provides specialized knowledge and patterns for Biome development.
Quality Hooks
This plugin includes hooks that ensure Biome checks pass before completing work. The hooks use @thebushidocollective/han to support both single-package and monorepo projects.
Monorepo Support
The hooks automatically detect directories with biome.json and run Biome checks in each:
han hook run --fail-fast --dirs-with biome.json -- npx biome check .
This ensures all packages in your monorepo pass Biome validation before work is marked complete.
Installation
Install with npx (no installation required):
han plugin install jutsu-biome
License
Licensed under MIT - see repository for details.
Hooks
Token Usage Notice
Hooks run automatically during Claude Code sessions and their output is sent to the model for processing. This may increase token usage and associated costs. Consider disabling hooks you don't need via han-config.yml.
Stop
Runs when the main Claude Code agent has finished responding. Can verify task completion, check quality gates, or ensure documentation requirements are met before the session ends.
SubagentStop
Runs when a Claude Code subagent (Task tool call) has finished responding. Can validate subagent outputs, enforce quality standards, or trigger additional workflows after delegated tasks complete.