mcpField
G
gitnexus-debugging

gitnexus-debugging

github.com/mindfold-aiDevelopment15.1k86 installsUpdated 6w ago
Repository

About gitnexus-debugging

gitnexus-debugging is a GitNexus skill for developers investigating errors and unexpected behavior. It guides code search, caller and callee inspection, and execution-flow tracing to help locate likely causes.

Key features

  1. 01Search code related to an error
  2. 02Inspect callers and callees
  3. 03Trace execution flows
  4. 04Write custom call-chain queries
  5. 05Check changes for regressions

Use cases

  1. 01Trace the origin of an error message
  2. 02Investigate an endpoint returning 500
  3. 03Follow data flow behind a wrong result
  4. 04Check recent changes for affected flows

MCP support

The skill uses GitNexus tools such as query, context, cypher, and detect_changes, and reads GitNexus repository process resources.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mindfold-ai/trellis --skill gitnexus-debugging

After installing, type/gitnexus-debuggingin Claude Code to confirm it loaded.

Details

From the project README

Debugging with GitNexus

When to Use

  • "Why is this function failing?"
  • "Trace where this error comes from"
  • "Who calls this method?"
  • "This endpoint returns 500"
  • Investigating bugs, errors, or unexpected behavior

Workflow

1. query({query: "<error or symptom>"})            → Find related execution flows
2. context({name: "<suspect>"})                    → See callers/callees/processes
3. READ gitnexus://repo/{name}/process/{name}                → Trace execution flow
4. cypher({query: "MATCH path..."})                 → Custom traces if needed

If "Index is stale" → run node .gitnexus/run.cjs analyze in terminal.

Checklist

- [ ] Understand the symptom (error message, unexpected behavior)
- [ ] query for error text or related code
- [ ] Identify the suspect function from returned processes
- [ ] context to see callers and callees
- [ ] Trace execution flow via process resource if applicable
- [ ] cypher for custom call chain traces if needed
- [ ] Read source files to confirm root cause

Debugging Patterns

SymptomGitNexus Approach
Error messagequery for error text → context on throw sites
Wrong return valuecontext on the function → trace callees for data flow
Intermittent failurecontext → look for external calls, async deps
Performance issuecontext → find symbols with many callers (hot paths)
Recent regressiondetect_changes to see what your changes affect

Tools

query — find code related to error:

query({query: "payment validation error"})
→ Processes: CheckoutFlow, ErrorHandling
→ Symbols: validatePayment, handlePaymentError, PaymentException

context — full context for a suspect:

context({name: "validatePayment"})
→ Incoming calls: processCheckout, webhookHandler
→ Outgoing calls: verifyCard, fetchRates (external API!)
→ Processes: CheckoutFlow (step 3/7)

cypher — custom call chain traces:

MATCH path = (a)-[:CodeRelation {type: 'CALLS'}*1..2]->(b:Function {name: "validatePayment"})
RETURN [n IN nodes(path) | n.name] AS chain

Example: "Payment endpoint returns 500 intermittently"

1. query({query: "payment error handling"})
   → Processes: CheckoutFlow, ErrorHandling
   → Symbols: validatePayment, handlePaymentError

2. context({name: "validatePayment"})
   → Outgoing calls: verifyCard, fetchRates (external API!)

3. READ gitnexus://repo/my-app/process/CheckoutFlow
   → Step 3: validatePayment → calls fetchRates (external)

4. Root cause: fetchRates calls external API without proper timeout

Comments

Markdown supported