Quick Start

Get productive with XibeCode in minutes. This guide walks you through your first autonomous coding session and introduces you to the key features.

Your First Task (CLI)

The run command lets XibeCode autonomously complete coding tasks. Just describe what you want:

xibecode run "Create a Python script that prints hello world"

XibeCode will read your project, create the file, and verify it works — all autonomously.

For a more realistic first task:

# Add a simple healthcheck endpoint to an Express API
xibecode run "Add GET /health that returns { status: 'ok' } and tests for it" --mode agent

Interactive Chat (CLI & WebUI)

For iterative development and quick questions, use chat mode:

xibecode chat

This starts both the terminal UI and the WebUI (browser) in sync. In chat mode you can:

• Ask questions about your codebase
• Request code changes step by step
• Switch between agent personas with /mode
• Toggle tool execution with tools on/off
• Type exit or quit to leave

Agent Modes (Personas)

XibeCode features several core agent personas, each optimized for different tasks. Switch modes to get specialized assistance:

# In chat mode, switch personas
/mode plan      # Aria the Architect - planning and analysis
/mode agent     # Default mode - full coding capabilities
/mode debugger  # Dex the Detective - bug hunting and fixing
/mode tester    # Tess the QA Engineer - testing and quality
/mode security  # Sentinel the Guardian - security audits
/mode review    # Nova the Critic - code reviews

Key Personas

Run Command Options

xibecode run [prompt] [options]

Options:
  -f, --file <path>           Read prompt from a file
  -m, --model <model>         AI model to use (default: claude-sonnet-4-5-20250929)
  -b, --base-url <url>        Custom API base URL
  -k, --api-key <key>         API key (overrides config)
  -d, --max-iterations <num>  Maximum iterations (default: 50)
  -v, --verbose               Show detailed logs
  --dry-run                   Preview changes without making them
  --changed-only              Focus only on git-changed files
  --mode <mode>               Start in a specific agent mode

Example Tasks

Build a Feature (CLI)

xibecode run "Add user authentication to the Express API:
- POST /auth/register
- POST /auth/login
- JWT token generation
- Middleware to protect routes"

Fix a Bug (CLI)

xibecode run "The tests in test/user.test.js are failing.
Debug and fix the issues." --verbose

Refactor Code

xibecode run "Refactor src/ to use TypeScript:
- Convert all .js files to .ts
- Add type annotations
- Create types.ts for shared types"

Generate Tests

xibecode run "Write comprehensive tests for userController.js:
- Test all endpoints
- Test error cases
- Use Jest
- Achieve >80% coverage"

Preview Changes (Dry Run)

xibecode run "Refactor authentication module" --dry-run

Focus on Changed Files

xibecode run "Fix linting errors in changed files" --changed-only

Use a Specific Mode

# Start in planning mode
xibecode run "Analyze this codebase and suggest improvements" --mode plan

# Start in debugging mode
xibecode run "Find the bug causing the API timeout" --mode debugger

First Hour with the WebUI

Once you have xibecode chat or xibecode ui --open running:

1. Open the WebUI at http://localhost:3847.
2. In the left activity bar, select Chat and send a message like:

   Help me understand this project and suggest a small first task.

3. Switch modes from the dropdown or with /mode:
   • /mode plan to analyze and plan.
   • /mode agent to implement.
   • /mode tester to focus on tests.
4. Open files from the file tree, and use the terminal panel to see commands and tests being run.
5. For security-focused projects, try:

   /mode pentest
   Pentest this project and generate pentest-report.md with a score out of 100.

How XibeCode Works

When you give XibeCode a task, it follows this autonomous loop:

1. Read — Analyzes your project structure, reads relevant files
2. Plan — Breaks down the task into steps
3. Execute — Creates/edits files, runs commands using 40+ tools
4. Verify — Runs tests, checks for errors
5. Iterate — Fixes any issues until the task is complete

The entire process is autonomous — XibeCode continues iterating until the task is done or it reaches the maximum iteration limit. It has built-in loop detection to prevent infinite loops.

Key Features

Smart Context Discovery

XibeCode automatically discovers related files by following imports, finding tests, and understanding project configuration.

Automatic Backups

Every file edit creates a timestamped backup. You can revert to any previous state:

# In chat mode
/revert src/app.ts  # Revert to previous version

Git Integration

XibeCode can create checkpoints before making changes:

xibecode run "Refactor the database layer (create checkpoint first)"

Test Integration

XibeCode auto-detects your test runner (Vitest, Jest, pytest, Go test, etc.) and runs tests to verify changes.

Safety Controls

Dangerous commands are blocked, and risky operations are flagged:

• Dry-run mode for safe previews
• Risk assessment before execution
• Command blocking for destructive operations
• Safer alternatives suggested when possible

Neural Memory

XibeCode learns from your project over time. It remembers patterns, preferences, and lessons learned:

# The agent automatically stores lessons
# You can also manually teach it
xibecode chat
> Remember that we use Prisma for database access in this project

Next Steps

• Agent Modes — Deep dive into the core personas
• Pentest Mode — Learn how to dynamically test your app’s security
• Configuration — Configure XibeCode for your workflow
• Tools Reference — Explore all 40+ available tools
• MCP Integration — Set up extended capabilities
• Examples — See more real-world tasks