A repository scanning and symbol mapping tool that builds a fast, searchable JSON index of classes, functions, and variables using Python AST and ripgrep.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install codebase-index
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install codebase-index using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Codebase Index?
Codebase Index is a system designed to help AI agents understand entire code repositories at depth, inspired by the advanced codebase indexing capabilities found in Claude Code. While tools like codebytelens focus purely on single-file analysis, Codebase Index provides a full-repository overview by scanning project directories to build a searchable database of symbols.
The system is built from scratch utilizing the Python Abstract Syntax Tree (ast) module alongside ripgrep for lightning-fast scanning. It accurately extracts code structural definitions such as classes, functions, variables, and code imports. This structure enables developer agents to gain instant repository intelligence without wasting LLM context windows on unnecessary code reading.
Codebase Index Use Cases
- Building a map of a large code repository for an AI agent to locate relevant functions or modules.
- Accelerating symbol searches across multiple directories without manual grep searching.
- Filtering repository code structures by specific definitions like classes or function declarations.
- Gathering comprehensive docstrings and codebase statistics to auto-generate technical overviews.
How Codebase Index Works
- Directory Scanning: The tool scans the target project directory, ignoring irrelevant files and prioritizing readable source files.
- Symbol Extraction: It uses Python's ast module and ripgrep to extract comprehensive definitions including class names, functions, variables, lines, docstrings, and imports.
- Index Generation: Collected metadata is compiled into a structured, highly optimized
index.jsonfile. - Query Interface Execution: The system opens CLI workflows allowing developers or Openclaw Skills agents to query the structured map by name, filter by code type, or match patterns via fuzzy searching.
Codebase Index Setup
Ensure you have python3 installed on your system as it is a required dependency for running the indexer.
# Clone or locate the skill in your environment
# Run a repository scan to generate your first index
python3 indexer.py scan /path/to/project --output project-index.json
Codebase Index Data Schema & Taxonomy
The output schema generated by this Openclaw Skills module is a clean JSON structure containing an array of extracted symbols. Below is an overview of the fields generated:
| Field | Type | Description |
|---|---|---|
symbols |
Array | A collection of all extracted structural components from the codebase |
symbols[].name |
String | The exact identifier name of the class, function, or variable |
symbols[].type |
String | Structural classification (e.g., class, function) |
symbols[].file |
String | Relative filepath location within the repository |
symbols[].line |
Integer | Exact line number where the definition begins |
symbols[].docstring |
String | Extracted inline developer documentation or string comments |
symbols[].methods |
Array | (Optional) List of method names contained within a class definition |
Codebase Index Advanced Features
- Granular Type Filtering: Easily query codebases specifically for function names, variables, or class implementations using target query filters.
- Full Repository Statistics: Generate structural summaries and metrics about files and definitions across the workspace using the built-in stats command.
- Fuzzy Matching Capabilities: Leverage powerful regex and query logic to lookup components even when only partial names are known.
SKILL.md
Loading
Related Openclaw Skills
Agent Harness Builder
Design, structure, and deploy complex multi-agent orchestrations with a complete blueprint and document handoff system.
Foresea
An AI agent forecasting skill that integrates Polymarket and Kalshi predictive analysis, model-vs-market edge tracking, and calibrated probability intelligence into your OpenClaw setup.
AI Test Engineer
An expert AI testing assistant transforming junior engineers into masters by implementing a 7-phase, 48-module full-lifecycle QA framework.
E-Store Skill
A powerful integration skill enabling AI agents to search, browse, download, and install skills, MCP servers, and comprehensive agent solutions directly from the e-store marketplace.
Remote Dispatch
Remote Dispatch bridges mobile messaging and desktop automation, allowing users to remotely control their computer via QQBot and computer-use scripts.
Google Flow Video Automation
An automation tool that leverages Chrome CDP to programmatically generate, optimize, and download AI videos on Google Flow.
Featured*
