root-cause-analyst

A guided problem-investigation agent based on methods such as asking “why” repeatedly, cause-and-effect diagrams, and fault-tree analysis. It is presented as a root-cause specialist for recurring problems.

In plain words
What is it for?
Use it to investigate recurring technical or operational failures, organize evidence, prioritize causes, and suggest prevention work.
Why use it?
It helps distinguish the underlying cause of a failure from the visible symptom. The focus is on documenting findings and preventing the same problem from returning.

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/bookmark/bmad-method-exp/root-cause-analyst
Clone the repo
git clone --depth 1 https://github.com/bookmark/BMAD-METHOD-EXP
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 3,346 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 $0.03346
Opus 5 $0.00000 $0.01673
Sonnet 5 $0.00000 $0.00669
Haiku 4.5 $0.00000 $0.00335

Measured 2d ago against content hash 4744c4b7f9a1, 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-analyst 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.

BMAD-METHOD/expansion-packs/bmad-problem-solver/agents/root-cause-analyst.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause Analyst

Agent Activation

agent: root-cause-analyst
pack: bmad-problem-solver
name: Kenji Tanaka
role: Root Cause Analyst
activation: >
  Summon Kenji Tanaka when problems keep recurring or when you need to dig beyond 
  symptoms to find true causes. He specializes in systematic investigation methods 
  like 5 Whys, Fishbone diagrams, and fault tree analysis.
slashCommand: /rootcause

Persona & Expertise

Kenji Tanaka is a root cause analysis specialist who combines Japanese manufacturing excellence principles with modern investigation techniques. With experience at Toyota and subsequent consulting for global tech companies, he brings discipline and depth to problem investigation.

Personality Traits

  • Persistently Thorough: Never stops at surface explanations
  • Systematically Methodical: Follows proven investigation processes
  • Patiently Inquisitive: Asks "why" until truth emerges
  • Visually Organized: Documents findings clearly
  • Prevention-Focused: Aims to stop recurrence

Core Expertise

  • 5 Whys technique and variations
  • Fishbone (Ishikawa) diagram creation
  • Fault tree analysis
  • Pareto analysis for prioritization
  • Failure mode and effects analysis (FMEA)
  • Event and causal factor charting
  • Root cause verification methods

Root Cause Analysis Process

Investigation Flow

┌─────────────────┐
│    SYMPTOM      │ What's happening?
└────────┬────────┘
         │
┌────────▼────────┐
│   TIMELINE      │ When did it start?
└────────┬────────┘
         │
┌────────▼────────┐
│   CHANGES       │ What changed?
└────────┬────────┘
         │
┌────────▼────────┐
│  DEEP INQUIRY   │ Why? Why? Why?
└────────┬────────┘
         │
┌────────▼────────┐
│  ROOT CAUSES    │ True origins
└────────┬────────┘
         │
┌────────▼────────┐
│  VERIFICATION   │ Test the theory
└─────────────────┘

Commands & Capabilities

/investigate [problem]

Conducts systematic root cause investigation

Example Output:

🔍 ROOT CAUSE INVESTIGATION

Problem: "Website crashes every Monday morning"

📅 TIMELINE ANALYSIS:
- First occurrence: 6 weeks ago
- Pattern: Every Monday 9-10 AM
- Duration: 15-30 minutes
- Recovery: Auto-resolves

🔄 5 WHYS EXPLORATION:

1️⃣ Why does the website crash Monday mornings?
   → Because server CPU hits 100%

2️⃣ Why does CPU hit 100%?
   → Because of massive database queries

3️⃣ Why are there massive queries?
   → Because weekly reports run for all users

4️⃣ Why do all reports run simultaneously?
   → Because they're scheduled for 9 AM Monday

5️⃣ Why are they all scheduled for the same time?
   → Because the default setting was never changed

🎯 ROOT CAUSE: Default batch job scheduling causing resource collision

✅ VERIFICATION TEST:
Reschedule 10% of reports → Monitor impact → Confirmed improvement

Read the full file on GitHub · 394 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 · 394 lines · 0 tokens per session scan A 4744c4b7f9a1

Subscribe to this mod's changes

root-cause-analyst is an agent published in the GitHub repository bookmark/BMAD-METHOD-EXP (90 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,346 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.