gitnexus-debugging

Trace bugs and errors through indexed codebases using GitNexus call graphs and Cypher queries.

1|Updated Jul 27, 2023
One-click install
npx skills add https://github.com/AlexTheGuitarGuy/.dotfiles --skill gitnexus-debugging-alextheguitarguy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gitnexus-debugging
Source: https://github.com/AlexTheGuitarGuy/.dotfiles/tree/main/claude/.claude/skills/gitnexus-debugging
Command: npx skills add https://github.com/AlexTheGuitarGuy/.dotfiles --skill gitnexus-debugging-alextheguitarguy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Debugging unfamiliar or large codebases requires manually tracing call chains and error origins, which is slow and error-prone. This Skill uses GitNexus's indexed code graph to locate error sources, trace execution flows, and identify root causes systematically. ## Core Features & Use Cases - Error Tracing: Search for error text with query, then inspect callers and callees of suspect functions with context to find where failures originate. - Call Chain Analysis: Use trace to find the shortest call path between two symbols, or write custom cypher queries for complex call chain traces. - Regression Investigation: Run detect_changes to see what recent changes affect, and read process resources to follow step-by-step execution flows. - Use Case: When a payment endpoint returns 500 intermittently, query for the error handling flow, inspect the suspect function's outgoing calls, and discover that an external API call lacks a proper timeout. ## Quick Start Ask the AI to trace why a specific function or endpoint is failing using GitNexus, starting with the error message or symptom you observed.

Frequently Asked Questions about gitnexus-debugging

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

FAQPage Schema
How do I trace where an error comes from in my codebase?▼

Start with query using the error text to find related execution flows and symbols, then run context on the suspect function to see its callers and callees. Read the process resource to follow the execution flow step by step until you confirm the root cause in source files.

How to find the call chain between two functions?▼

Use the trace tool with from and to symbol names to get the shortest call chain in one call, including hop count and edge confidence. When no path exists, trace reports the furthest reachable node, showing exactly where the chain breaks.

What should I do when multiple repositories are indexed in GitNexus?▼

Call list_repos first and pass the repo argument explicitly on every subsequent call. An omitted repo normally errors, but under an MCP policy with a configured default it resolves silently, which can trace the wrong codebase.

Why does GitNexus report a stale index during debugging?▼

A stale index describes code from before your recent changes, so traces may not reflect the current bug. Run node .gitnexus/run.cjs analyze in the terminal to refresh the index before trusting any diagnosis.

When should I use cypher instead of context for debugging?▼

Use cypher for custom call chain traces that context cannot express, such as matching variable-length CALLS paths between symbols. Always pass repo alongside the statement since the Cypher text itself names no repository.