research-codebase

Explore codebases with parallel sub-agents to document features and implementation details.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/hodor/claude-compass --skill research-codebase-hodor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-codebase
Source: https://github.com/hodor/claude-compass/tree/main/plugin/skills/research-codebase
Command: npx skills add https://github.com/hodor/claude-compass --skill research-codebase-hodor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables a thorough exploration and documentation of a codebase's current state by using parallel sub-agents to investigate and report findings.

Core Features & Use Cases

  • Parallel Research: Concurrently analyze various aspects of a codebase for a comprehensive overview.
  • Documentarian Focus: Emphasizes description over criticism, ensuring an unbiased documentation of the existing state.
  • Use Case: For developers who need a quick and detailed reference on how a component functions, or where specific functionalities are handled within the codebase.

Quick Start

Invoke the research-codebase skill with your specific research question: 'How does the payment processing feature work?'

Frequently Asked Questions about research-codebase

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze a codebase to understand how a specific feature works?

To analyze a codebase, you can research and document its current state using parallel sub-agents. This approach concurrently investigates code structure and implementation details to provide a comprehensive overview of specific features.

What is parallel codebase research and how does it help with software documentation?

Parallel codebase research uses multiple sub-agents to concurrently explore different aspects of your codebase. It helps software documentation by rapidly compiling detailed, unbiased descriptions of existing features and patterns.

Can I document implementation details for a large software project quickly?

You can document implementation details for a large software project quickly by parallelizing the exploration of its code structure. Multiple sub-agents concurrently analyze the codebase to deliver a detailed reference.

Does the parallel agents approach evaluate code quality or just describe it?

The parallel agents approach focuses on description over criticism, ensuring an unbiased documentation of the existing state. It emphasizes documenting current features and patterns rather than evaluating code quality.

How do I find where specific functionalities are handled within my codebase?

To find where specific functionalities are handled, you invoke the research-codebase skill with your question. It deploys parallel sub-agents to investigate the codebase and report detailed findings on those locations.