XibeCode

Tools Reference

40+ built-in tools across 8 categories for autonomous coding operations. File operations, git, shell, web search, testing, browser automation, memory, and more.

XibeCode provides 40+ built-in tools across 8 categories for autonomous coding operations. These tools are automatically available to the AI agent based on the current mode's permissions.

Tool Categories Overview

CategoryToolsDescription
File Operations8Read, write, edit, delete files
Directory Operations3List, search, create, move
Git Operations7Status, diff, checkpoints, revert
Shell & Code Search2Execute commands, grep code
Web Operations2Search, fetch URLs
Test Operations4Run tests, generate tests, analyze code
Memory Operations2Neural memory updates
Browser Operations8Screenshots, testing, performance, accessibility

File Operations

read_file

Read the contents of a file.

{ "path": "src/app.ts", "start_line": 1, "end_line": 100 }

read_multiple_files

Read multiple files at once for context.

{ "paths": ["src/app.ts", "src/utils.ts", "package.json"] }

write_file

Write content to a file (creates or overwrites).

{ "path": "src/new-file.ts", "content": "export const hello = 'world';" }

edit_file

Edit a file using search and replace.

{
  "path": "src/app.ts",
  "search": "const oldValue = 1;",
  "replace": "const newValue = 2;"
}

edit_lines

Edit specific line ranges in a file.

{
  "path": "src/app.ts",
  "start_line": 10,
  "end_line": 15,
  "content": "// New content"
}

insert_at_line

Insert content at a specific line.

{
  "path": "src/app.ts",
  "line": 5,
  "content": "import { newModule } from './module';"
}

verified_edit

Edit with verification — ensures the search pattern exists before replacing.

{
  "path": "src/app.ts",
  "search": "exact content to find",
  "replace": "replacement content"
}

delete_file

Delete a file.

{ "path": "src/deprecated.ts" }

Directory Operations

list_directory

{ "path": "src/", "recursive": false }

search_files

{ "pattern": "*.ts", "path": "src/" }

create_directory

{ "path": "src/new-feature/" }

move_file

{ "source": "src/old-name.ts", "destination": "src/new-name.ts" }

Git Operations

get_git_status

Returns staged, unstaged, and untracked files.

get_git_diff_summary

{ "staged": true }

get_git_changed_files

Get list of files changed in the current branch.

create_git_checkpoint

{ "message": "before auth refactor", "strategy": "stash" }

revert_to_git_checkpoint

{ "checkpoint_id": "stash@{0}" }

git_show_diff

{ "path": "src/app.ts" }

get_mcp_status

Get MCP server status.

Shell Commands

run_command

{
  "command": "npm install express",
  "cwd": "./",
  "timeout": 30000,
  "stdin": "input data"
}

Dangerous commands like rm -rf / are blocked automatically.

grep_code

{
  "pattern": "function.*async",
  "path": "src/",
  "include": "*.ts",
  "case_sensitive": false
}

Web Operations

{ "query": "typescript best practices 2024", "num_results": 5 }

fetch_url

{ "url": "https://api.example.com/data", "method": "GET" }

Test Operations

run_tests

{ "path": "src/", "filter": "auth", "verbose": true }

Supports: Vitest, Jest, Mocha, pytest, Go test, Cargo test.

get_test_status

Returns passed, failed, and skipped test counts.

Memory Operations

update_memory

{
  "key": "project_structure",
  "value": "This project uses Next.js with TypeScript"
}

remember_lesson

{
  "lesson": "Always run npm install after pulling changes",
  "context": "Build failures after git pull"
}

Browser Operations

XibeCode uses Playwright under the hood for browser automation and works best with agent-browser as the primary interface for AI-driven browser control. In practice:

  • Use run_command + agent-browser for interactive flows, snapshots, and ref-based navigation.
  • Use these Playwright-backed browser tools for structured audits, screenshots, and tests.

take_screenshot

{ "url": "http://localhost:3000", "path": "screenshot.png", "full_page": true }

get_console_logs

Get browser console logs and errors from a page.

run_visual_test

Run visual regression testing by comparing screenshots against a baseline.

check_accessibility

Run accessibility audit (WCAG compliance) — checks alt text, labels, headings, contrast.

measure_performance

Measure Core Web Vitals: FCP, LCP, CLS, TTI, DOM Content Loaded.

test_responsive

Test a page across multiple viewport sizes with screenshots at each breakpoint.

capture_network

Capture all network requests made during page load.

run_playwright_test

{
  "test_path": "tests/homepage.spec.ts",
  "browser": "chromium",
  "timeout": 120000
}

Context Operations

get_context

Get smart context for a file (imports, tests, related files).

revert_file

Revert a file to its last backed-up state.

Skills Operations

search_skills_sh

Search for skills on skills.sh marketplace.

install_skill_from_skills_sh

Install a skill from skills.sh.

Tool Permissions by Mode

  • read_only: read_file, read_multiple_files, list_directory, search_files
  • write_fs: write_file, edit_file, edit_lines, insert_at_line, delete_file, move_file, create_directory
  • git_read: get_git_status, get_git_diff_summary, get_git_changed_files, git_show_diff
  • git_mutation: create_git_checkpoint, revert_to_git_checkpoint
  • shell_command: run_command
  • tests: run_tests, get_test_status
  • network: web_search, fetch_url
  • context: grep_code, get_context

Safety Features

  • Command Blocking — Dangerous commands like rm -rf / are blocked
  • Risk Assessment — High-risk operations are flagged with warnings
  • Automatic Backups — Files are backed up before editing
  • Dry-Run Mode — Preview changes without executing
  • Mode Permissions — Tools are restricted based on current mode

Extending Tools

You can add custom tools via:

Next Steps

Ctrl+I
Assistant

How can I help?

Ask me about configuration, installation, or specific features.