explore-codebase

Navigate codebase structure and trace code relationships using a knowledge graph.

Updated Sep 8, 2026
One-click install
npx skills add https://github.com/bmiit145/leadBee --skill explore-codebase-bmiit145
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: explore-codebase
Source: https://github.com/bmiit145/leadBee/tree/main/.gemini/skills/explore-codebase
Command: npx skills add https://github.com/bmiit145/leadBee --skill explore-codebase-bmiit145

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Understanding a large or unfamiliar codebase is slow when you have to read files one by one. This Skill uses a code knowledge graph to answer structural questions—where a function is called, which modules exist, how execution flows—without manually grepping through the repository. ## Core Features & Use Cases - Architecture Discovery: Get codebase statistics, community/module overviews, and high-level architecture before diving into details. - Relationship Tracing: Find callers, callees, and imports of any function or class, and inspect execution flows end to end. - Token-Efficient Exploration: Retrieve minimal context for a task first, targeting completion in five or fewer tool calls. - Use Case: Before refactoring a shared utility, use the graph to list every caller of the function and read the relevant tests, so the change does not break downstream code. ## Quick Start Ask the assistant to explore this codebase and show which modules call the authentication service.

Frequently Asked Questions about explore-codebase

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

FAQPage Schema
How do I explore a large codebase quickly?▼

Start with graph statistics and the architecture overview to see major modules, then drill into specific communities and use semantic search to locate functions. This top-down approach avoids reading files one by one.

How to find all callers of a function in a codebase?▼

Use the graph query tool with the callers_of pattern on the target function to list every call site. You can also use callees_of and imports_of to trace dependencies in the other direction.

What is a code knowledge graph used for?▼

A code knowledge graph indexes functions, classes, files, and their relationships so you can query structure instead of grepping text. It supports architecture overviews, community detection, execution flow analysis, and semantic node search.

Does graph-based exploration replace reading source code?▼

No. The graph narrows the scope to relevant files and symbols, but you should still read the implementation and its tests before changing code. It is a navigation aid, not a substitute for the source.

How do I reduce token usage when exploring code with AI tools?▼

Request minimal context for your task first and use the minimal detail level on graph calls, escalating only when needed. The workflow targets completing a review or debug task in five or fewer tool calls.