debug-RCA

A guided debugging procedure for finding the cause of a reported software problem. It covers reproduction, information gathering, isolating the cause, and checking runtime, logic, and performance issues.

In plain words
What is it for?
Use it to reproduce bugs, inspect logs and recent changes, narrow problems with techniques such as Git bisect, and investigate errors, incorrect behavior, or slow code.
Why use it?
It turns a vague bug report into a sequence of checks, helping narrow down where and when the problem began.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/echoingvesper/mcp-task-orchestrator/debug-rca
Clone the repo
git clone --depth 1 https://github.com/EchoingVesper/mcp-task-orchestrator

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00596
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 2d ago against content hash 05ae969132fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-RCA scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Test with curl/Postman first
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • debug-RCA — 100% identical, 220 lines differ
.claude/commands/development/debug-RCA.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Issue

Systematically debug and diagnose the reported problem.

Problem Description

$ARGUMENTS

Debugging Process

  1. Reproduce the Issue

    • Get exact steps to reproduce
    • Verify you can see the same problem
    • Note any error messages or logs
    • Document the expected vs actual behavior
  2. Gather Information

    # Check recent changes
    git log --oneline -10
    
    # Look for error patterns in logs
    # Search for related error messages
    
  3. Isolate the Problem

    • Binary Search: Comment out code sections to narrow down
    • Git Bisect: Find when the bug was introduced
    • Logging: Add strategic log statements
    • Debugger: Set breakpoints if applicable
  4. Common Debugging Strategies

    For Runtime Errors

    • Read the full stack trace
    • Identify the exact line causing the error
    • Check variable values at that point
    • Verify assumptions about data types

    For Logic Errors

    • Add print/log statements to trace execution
    • Verify each step produces expected results
    • Check boundary conditions
    • Test with minimal reproducible example

    For Performance Issues

    • Add timing measurements
    • Check for N+1 queries
    • Look for inefficient algorithms
    • Profile if necessary

    For Integration Issues

    • Verify external service is accessible
    • Check authentication/credentials
    • Validate request/response formats
    • Test with curl/Postman first
  5. Root Cause Analysis

    • Why did this happen?
    • Why wasn't it caught earlier?
    • Are there similar issues elsewhere?
    • How can we prevent this class of bugs?
  6. Implement Fix

    • Fix the root cause, not just symptoms
    • Add defensive programming if needed
    • Consider edge cases
    • Keep fix minimal and focused, follow KISS
  7. Verify Resolution

    • Confirm original issue is fixed
    • Check for regression
    • Test related functionality
    • Add test to prevent recurrence

Read the full file on GitHub · 113 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 113 lines · 0 tokens per session scan A 05ae969132fc

Subscribe to this mod's changes

debug-RCA is a command published in the GitHub repository EchoingVesper/mcp-task-orchestrator (28 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 596 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.