codebase-memory

Query a codebase knowledge graph to trace function calls and dependencies.

2|Updated May 2, 2025
One-click install
npx skills add https://github.com/adryanev/.dotfiles --skill codebase-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codebase-memory
Source: https://github.com/adryanev/.dotfiles/tree/main/.agents/skills/codebase-memory
Command: npx skills add https://github.com/adryanev/.dotfiles --skill codebase-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Structural queries against large codebases are time-consuming and error-prone; this skill lets you leverage a codebase knowledge graph to reveal architecture, dependencies, and call relationships so you can reason about systems without grep.

Core Features & Use Cases

  • Explore architecture and module boundaries using a graph representation of code.
  • Trace inbound and outbound calls, identify callers, surface dead code, and detect high fan-out areas.
  • Perform impact analysis and cross-service reasoning with graph queries to guide refactoring or auditing.

Quick Start

Trace a function's callers and dependencies to map its impact across the codebase.

Frequently Asked Questions about codebase-memory

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

FAQPage Schema
How do I trace function callers and dependencies across a codebase?

Trace function callers and dependencies by mapping the codebase knowledge graph. This reveals call relationships and structural architecture, allowing you to perform cross-module impact analysis without relying on grep.

What is a codebase knowledge graph used for in static analysis?

A codebase knowledge graph represents static-analysis output as interconnected nodes. It maps architecture and module boundaries to help you reason about system structure, trace inbound calls, and identify high fan-out areas.

How do I identify dead code and high fan-out areas in a large repository?

Identify dead code and high fan-out areas by querying the codebase knowledge graph. The graph surfaces uncalled functions and tracks dependency density, guiding your refactoring and auditing efforts.

Do I need an indexed repository to query architecture and module boundaries?

Yes, querying architecture and module boundaries requires an indexed repository with a graph schema. This setup enables structural queries like trace_path and search_graph to map dependencies accurately.

What is the best way to perform cross-service impact analysis without grep?

Perform cross-service impact analysis by applying graph queries to a codebase knowledge graph. This approach reveals structural dependencies and caller relationships across modules, replacing manual text searches.

Can I get code snippets while tracing paths through a dependency graph?

Yes, you can retrieve code snippets while tracing paths by using the get_code_snippet query. This function extracts relevant code sections from the graph to contextualize dependency and caller relationships.