A Node.js CLI tool that automatically generates configuration files for various AI development tools from unified AI rule files. Features selective generation, comprehensive import/export capabilities, and supports major AI development tools with rules, commands, MCP, ignore files, and subagents. Uses the recommended .rulesync/rules/*.md structure, with full backward compatibility for legacy .rulesync/*.md layouts.

npm install -g rulesync
# or
pnpm add -g rulesync
# or
yarn global add rulesync
# or
bun add -g rulesync
# or
brew install rulesync

# And then
rulesync --version
rulesync --help

# Create necessary directories, sample rule files, and configuration file
npx rulesync init

On the other hand, if you already have AI tool configurations:

# Import existing files (to .rulesync/**/*)
npx rulesync import --targets claudecode    # From CLAUDE.md
npx rulesync import --targets cursor        # From .cursorrules
npx rulesync import --targets copilot       # From .github/copilot-instructions.md
npx rulesync import --targets claudecode --features rules,mcp,commands,subagents

# And more tool supports

# Generate unified configurations with all features
npx rulesync generate --targets "*" --features "*"

Rulesync supports both generation and import for All of the major AI coding tools:

• ✅: Supports project mode
• 🌏: Supports global mode
• 🎮: Supports simulated commands/subagents (Project mode only)
• 📦: Supports modular MCP (Experimental)

Team members can freely choose their preferred AI coding tools. Whether it's GitHub Copilot, Cursor, Cline, or Claude Code, each developer can use the tool that maximizes their productivity.

AI development tools evolve rapidly with new tools emerging frequently. With Rulesync, switching between tools doesn't require redefining your rules from scratch.

Enable hybrid development workflows combining multiple AI tools.

Avoid lock-in completely. If you decide to stop using Rulesync, you can continue using the generated rule files as-is.

Apply consistent rules across all AI tools, improving code quality and development experience for the entire team.

You can use global mode via Rulesync by enabling --global option.

Simulated commands and subagents allow you to generate simulated commands and subagents for copilot, cursor and codexcli. This is useful for shortening your prompts.

# Initialize new project (recommended: organized rules structure)
npx rulesync init

# Import existing configurations (to .rulesync/rules/ by default)
npx rulesync import --targets claudecode --features rules,ignore,mcp,commands,subagents

# Generate all features for all tools (new preferred syntax)
npx rulesync generate --targets "*" --features "*"

# Generate specific features for specific tools
npx rulesync generate --targets copilot,cursor,cline --features rules,mcp
npx rulesync generate --targets claudecode --features rules,subagents

# Generate only rules (no MCP, ignore files, commands, or subagents)
npx rulesync generate --targets "*" --features rules

# Generate simulated commands and subagents
npx rulesync generate --targets copilot,cursor,codexcli --features commands,subagents --simulated-commands --simulated-subagents

# Add generated files to .gitignore
npx rulesync gitignore

You can configure Rulesync by creating a rulesync.jsonc file in the root of your project.

Example:

// rulesync.jsonc
{
  // List of tools to generate configurations for. You can specify "*" to generate all tools.
  "targets": ["cursor", "claudecode", "geminicli", "opencode", "codexcli"],

  // Features to generate. You can specify "*" to generate all features.
  "features": ["rules", "ignore", "mcp", "commands", "subagents"],
  
  // Base directories for generation.
  // Basically, you can specify a `["."]` only.
  // However, for example, if your project is a monorepo and you have to launch the AI agent at each package directory, you can specify multiple base directories.
  "baseDirs": ["."],

  // Delete existing files before generating
  "delete": true,

  // Verbose output
  "verbose": false,

  // Advanced options
  "global": false,  // Generate for global(user scope) configuration files
  "simulatedCommands": false,  // Generate simulated commands
  "simulatedSubagents": false,  // Generate simulated subagents
  "modularMcp": false  // Enable modular-mcp for context compression (experimental, Claude Code only)

  // Deprecated experimental options (for backward compatibility)
  // "experimentalGlobal": false,
  // "experimentalSimulateCommands": false,
  // "experimentalSimulateSubagents": false
}

Example:

---
root: true # true that is less than or equal to one file for overview such as `AGENTS.md`, false for details such as `.agents/memories/*.md`
targets: ["*"] # * = all, or specific tools
description: "Rulesync project overview and development guidelines for unified AI rules management CLI tool"
globs: ["**/*"] # file patterns to match (e.g., ["*.md", "*.txt"])
agentsmd: # agentsmd and codexcli specific rules
  # Support for using nested AGENTS.md files for subprojects in a large monorepo.
  # This option is available only if root is false.
  # If subprojectPath is provided, the file is located in `${subprojectPath}/AGENTS.md`.
  # If subprojectPath is not provided and root is false, the file is located in `.agents/memories/*.md`.
  subprojectPath: "path/to/subproject"
cursor: # cursor specific rules
  alwaysApply: true
  description: "Rulesync project overview and development guidelines for unified AI rules management CLI tool"
  globs: ["*"]
---

# Rulesync Project Overview

This is Rulesync, a Node.js CLI tool that automatically generates configuration files for various AI development tools from unified AI rule files. The project enables teams to maintain consistent AI coding assistant rules across multiple tools.

...

Example:

---
description: 'Review a pull request' # command description
targets: ["*"] # * = all, or specific tools
---

target_pr = $ARGUMENTS

If target_pr is not provided, use the PR of the current branch.

Execute the following in parallel:

...

Example:

---
name: planner # subagent name
targets: ["*"] # * = all, or specific tools
description: >- # subagent description
  This is the general-purpose planner. The user asks the agent to plan to
  suggest a specification, implement a new feature, refactor the codebase, or
  fix a bug. This agent can be called by the user explicitly only.
claudecode: # for claudecode-specific rules
  model: inherit # opus, sonnet, haiku or inherit
---

You are the planner for any tasks.

Based on the user's instruction, create a plan while analyzing the related files. Then, report the plan in detail. You can output files to @tmp/ if needed.

Attention, again, you are just the planner, so though you can read any files and run any commands for analysis, please don't write any code.

Example:

{
  "mcpServers": {
    "serena": {
      "description": "Code analysis and semantic search MCP server",
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/oraios/serena",
        "serena",
        "start-mcp-server",
        "--context",
        "ide-assistant",
        "--enable-web-dashboard",
        "false",
        "--project",
        "."
      ],
      "env": {}
    },
    "context7": {
      "description": "Library documentation search server",
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@upstash/context7-mcp"
      ],
      "env": {}
    }
  }
}

Rulesync supports modular-mcp for context compression. When enabled with --modular-mcp, it generates both .mcp.json and modular-mcp.json files for Claude Code.

Benefits:

• Reduces context usage by loading tool schemas on-demand
• Better scalability when using many MCP servers
• Improved performance with large tool collections

Requirements:

• Each MCP server must have a description field (required when modularMcp is enabled)
• Currently only supported for Claude Code

Usage:

# Enable modular-mcp via CLI
npx rulesync generate --targets claudecode --features mcp --modular-mcp

# Or via configuration file
{
  "modularMcp": true
}

Generated files:

• .mcp.json - Contains modular-mcp proxy configuration
• modular-mcp.json - Contains actual MCP server configurations

For more information, see the modular-mcp documentation.

Example:

tmp/
credentials/

You can use global mode via Rulesync by enabling --global option. It can also be called as user scope mode.

Currently, supports rules and commands generation for Claude Code. Import for global files is supported for rules and commands.

1. Create an any name directory. For example, if you prefer ~/.aiglobal, run the following command.

   mkdir -p ~/.aiglobal

2. Initialize files for global files in the directory.

   cd ~/.aiglobal
   npx rulesync init

3. Edit ~/.aiglobal/rulesync.jsonc to enable global mode.

   {
     "global": true
   }

4. Edit ~/.aiglobal/.rulesync/rules/overview.md to your preferences.

   ---
   root: true
   ---
   # The Project Overview
   ...

5. Generate rules for global settings.

   # Run in the `~/.aiglobal` directory
   npx rulesync generate

Simulated commands and subagents allow you to generate simulated commands and subagents for copilot, cursor, codexcli and etc. This is useful for shortening your prompts.

1. Prepare .rulesync/commands/*.md and .rulesync/subagents/*.md for your purposes.
2. Generate simulated commands and subagents for specific tools that are included in copilot, cursor, codexcli and etc.

   npx rulesync generate \
     --targets copilot,cursor,codexcli \
     --features commands,subagents \
     --simulated-commands \
     --simulated-subagents

3. Use simulated commands and subagents in your prompts.
   • Prompt examples:

     # Execute simulated commands. By the way, `s/` stands for `simulate/`.
     s/your-command
     
     # Execute simulated subagents
     Call your-subagent to achieve something.

Issues and Pull Requests are welcome!

For development setup:

git clone https://github.com/dyoshikawa/rulesync # Should be your fork repository url actually
cd rulesync
pnpm i
pnpm cicheck # Run code style check, type check, and tests

# Manual test using current code
pnpm dev generate -t claudecode -f "*"
pnpm dev import -t claudecode -f "*"

MIT License