root-cause-analyzer-quickstart

A quick-start agent for investigating the underlying cause of software problems rather than only their visible symptoms. It can be started interactively or given a problem description directly.

In plain words
What is it for?
Use it to investigate incidents such as checkout errors, timeouts, memory leaks, and deployment regressions, then receive findings, fixes, prevention steps, and code locations.
Why use it?
It helps organise debugging around evidence such as error messages, timing, frequency, environment, and recent changes.

Agent

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 agents/dnyoussef/context-cascade/root-cause-analyzer-quickstart
Clone the repo
git clone --depth 1 https://github.com/DNYoussef/context-cascade
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 1,189 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.01189
Opus 5 $0.00000 $0.00594
Sonnet 5 $0.00000 $0.00238
Haiku 4.5 $0.00000 $0.00119

Measured 2d ago against content hash f6fed2d085f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

root-cause-analyzer-quickstart scanned grade A with 0 findings against 26 rules in 11 categories β€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency β€” 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/root-cause-analyzer-quickstart.md Β· 191 lines

How it starts

The opening of the file, as written. The whole thing β€” 191 lines β€” stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause Analyzer - Quick Start Guide

πŸš€ Quick Usage

Using the Skill (Easiest)

# Interactive mode - you'll be prompted for details
/reverse-engineer-debug

# Direct with issue description
/reverse-engineer-debug "Users getting 500 errors on checkout after deployment"

Using Task Tool (Advanced)

Task({
  subagent_type: "root-cause-analyzer",
  description: "Debug timeout issue",
  prompt: "Investigate why API calls timeout after 30s. Started yesterday after updating SDK."
})

πŸ“ What to Provide

For best results, include:

  • βœ… Error message (exact text)
  • βœ… When it started (deployment, change, etc.)
  • βœ… How often (always, intermittent, %)
  • βœ… Where (production, staging, local)
  • βœ… What changed (code, config, dependencies)

πŸ“Š What You Get

The agent provides:

  1. Executive Summary - Quick overview
  2. Investigation Trail - What was checked and why
  3. Root Cause - The real problem (not symptoms)
  4. Solution - How to fix it properly
  5. Prevention - How to avoid it in the future
  6. Code References - Exact file:line locations

🎯 Example Session

You: /reverse-engineer-debug "Memory leak causing crashes after 2 hours"

Agent:
# Root Cause Analysis Report

## Executive Summary
- **Problem**: Application exhausts memory and crashes
- **Root Cause**: Event listeners accumulate without cleanup
- **Location**: src/components/Dashboard.jsx:45
- **Fix**: Add cleanup in componentWillUnmount
- **Priority**: Critical

## Investigation Process
1. Profiled memory growth β†’ confirmed leak
2. Tracked object retention β†’ found event listeners
3. Analyzed component lifecycle β†’ missing cleanup
4. Validated with heap snapshot β†’ confirmed cause

## Root Cause
Event listeners registered in componentDidMount but never removed.
Each render adds new listeners without removing old ones.

## Solution
```javascript
componentWillUnmount() {
  window.removeEventListener('resize', this.handleResize);
  eventBus.off('update', this.handleUpdate);
}

Prevention

  • Add memory profiling to CI/CD
  • Use linter rules for listener cleanup
  • Add test for component unmount behavior

Read the full file on GitHub Β· 191 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 Β· 191 lines Β· 0 tokens per session scan A f6fed2d085f6

Subscribe to this mod's changes

root-cause-analyzer-quickstart is an agent published in the GitHub repository DNYoussef/context-cascade (32 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,189 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

trellis-check

Code quality check expert. Reviews code changes against specs and self-fixes issues.

yuqie6/ProductFlow Β· 20 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork Β· 106 tokens

exec-remote-slurm

Execute a TensorRT-LLM workload on a remote Slurm cluster via SSH. Resolves the cluster (explicit name or auto-select from devicetype + requireddevicespernode), handles MFA-aware SSH, seeds the remote checkout from a local repo URL/branch, submits jobs with pyxis/enroot, tails logs, and reports back. The orchestrator…

NVIDIA/TensorRT-LLM Β· 107 tokens

gtm-technical

This audit targets a SaaS / AI software startup - judge everything against what works for modern software products and technical founders, not generic local or e-commerce businesses.

adaptico/adaptico-os Β· 0 tokens

platform-engineer

Platform and forge specialist β€” CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.

ulises-jeremias/agent-toolkit Β· 88 tokens

CodeQL Permissions Auditor

Analyze workflow permission issues and apply fixes.

dryvist/claude-code-plugins Β· 12 tokens