root-cause-analyzer

An investigative coding agent that traces bugs and system failures back to their underlying causes. It studies errors, execution paths, dependencies, data flow, configuration, and external integrations.

In plain words
What is it for?
Use it to investigate stack traces, type or memory issues, dependency and configuration failures, timing problems, broken API contracts, and error propagation.
Why use it?
It helps distinguish the visible symptom from the condition that actually caused the problem, reducing guesswork during debugging.

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
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 2,800 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 $0.02800
Opus 5 $0.00000 $0.01400
Sonnet 5 $0.00000 $0.00560
Haiku 4.5 $0.00000 $0.00280

Measured 2d ago against content hash 3e46ea79c8a1, 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 scanned grade A with 0 findings 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.

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.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause Analyzer Agent - Documentation

Overview

The Root Cause Analyzer is a specialized investigative agent designed to perform systematic reverse engineering and forensic analysis to find the real underlying causes of bugs, failures, and system issues. Unlike simple debugging that treats symptoms, this agent employs rigorous methodologies to identify and address fundamental problems.

Key Features

🔍 Reverse Engineering Excellence

  • Works backwards from errors to trace root causes
  • Reconstructs timelines and execution paths
  • Maps dependencies and data flows
  • Analyzes state transitions and mutations

🧪 Systematic Investigation

  • Generates and tests multiple hypotheses
  • Uses eliminative reasoning to rule out false leads
  • Collects and analyzes forensic evidence
  • Distinguishes symptoms from root causes
  • Validates findings with comprehensive testing

🎯 Deep Analysis Capabilities

  • Code-Level: Stack traces, execution flows, type issues, memory problems
  • System-Level: Dependencies, configurations, resource contention, timing issues
  • Integration-Level: API contracts, data formats, error propagation
  • Environmental: OS, runtime, libraries, external services
  • Design-Level: Architecture flaws, missing requirements, wrong abstractions

📊 Structured Reporting

  • Executive summaries for quick understanding
  • Detailed investigation trails for transparency
  • Clear root cause explanations with technical depth
  • Actionable solution designs
  • Prevention strategies to avoid recurrence

When to Use

Perfect For:

✅ Mysterious or intermittent bugs ✅ Production incidents requiring investigation ✅ System failures or crashes ✅ Performance regressions ✅ Integration failures between components ✅ Post-deployment issues ✅ Legacy code problems ✅ Issues that reappear after "fixes"

Not Ideal For:

❌ Simple syntax errors (use standard debugging) ❌ Known issues with obvious causes ❌ Feature implementation (use coding agents) ❌ Code reviews (use review agents)

Read the full file on GitHub · 426 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 · 426 lines · 0 tokens per session scan A 3e46ea79c8a1

Subscribe to this mod's changes

root-cause-analyzer 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 2,800 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.