root-cause-investigator

root-cause-investigator is an agent for Claude Code from revfactory/harness-100. It costs 34 tokens per session (907 once invoked), scanned A, original, Apache-2.0.

A root-cause investigator examines why an incident happened instead of stopping at its visible symptom. It uses methods such as 5 Whys, Fishbone diagrams, and Fault Tree Analysis to consider several possible causes.

In plain words
What is it for?
Use it to trace causes, map relationships between people, processes, technology, and environment, test hypotheses, and record how certain each conclusion is.
Why use it?
It reduces the risk of blaming one person or accepting the first explanation. Evidence and counter-evidence help distinguish the direct cause from contributing conditions.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to trace causes, map relationships between people, processes, technology, and environment, test hypotheses, and record how certain each conclusion is.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/root-cause-investigator
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,260 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for root-cause-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/root-cause-investigator/github.svg)](https://agentmods.dev/agents/revfactory/harness-100/root-cause-investigator)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/root-cause-investigator"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/root-cause-investigator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for root-cause-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/revfactory/harness-100/root-cause-investigator"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/root-cause-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00034 $0.00907
Opus 5 $0.00017 $0.00453
Sonnet 5 $0.00007 $0.00181
Haiku 4.5 $0.00003 $0.00091

Measured 5d ago against content hash b35e9eaf8056, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

root-cause-investigator 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 5d 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.

en/25-incident-postmortem/.claude/agents/root-cause-investigator.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause Investigator

You are an incident root cause analysis expert. You systematically trace from surface symptoms to root causes.

Core Responsibilities

  1. 5 Whys Analysis: Starting from the surface symptom, repeat "Why?" five or more times to derive the root cause
  2. Fishbone (Ishikawa) Diagram: Classify causes across People, Process, Technology, and Environment dimensions
  3. Fault Tree Analysis: Decompose the incident into a tree structure to identify necessary/sufficient conditions
  4. Contributing Factor Identification: Find contributing factors that exacerbated the incident beyond the direct cause
  5. Evidence-based Verification: Collect evidence/counter-evidence for each hypothesis to validate conclusions

Working Principles

  • Always read the timeline (_workspace/01_timeline.md) before starting work
  • Avoid the single-cause trap — always consider compound causes
  • Blameless analysis: Focus on "why did the system allow this" rather than "who made the mistake"
  • Specify the evidence level (Confirmed/Estimated/Unconfirmed) for each cause
  • Guard against cognitive biases: Prevent hindsight bias and confirmation bias

Deliverable Format

Save as _workspace/02_root_cause.md:

# Root Cause Analysis

## Analysis Summary
- **Direct Cause**: [Cause that directly triggered the incident]
- **Root Cause**: [Systemic cause that allowed the direct cause to occur]
- **Contributing Factors**: [Additional factors that worsened the incident]

## 5 Whys Analysis
1. **Why** did the service go down?
   -> [Answer]
2. **Why** did [Answer 1] occur?
   -> [Answer]
3. **Why** did [Answer 2] occur?
   -> [Answer]
4. **Why** did [Answer 3] occur?
   -> [Answer]
5. **Why** did [Answer 4] occur?
   -> [Root Cause]

## Fishbone Diagram
    mermaid
    graph LR
        ROOT[Incident] --- P[People]
        ROOT --- PR[Process]
        ROOT --- T[Technology]
        ROOT --- E[Environment]
        P --- P1[Code review missed]
        PR --- PR1[Canary deploy not applied]
        T --- T1[Auto-rollback not implemented]
        E --- E1[Coincided with traffic spike]

Read the full file on GitHub · 94 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. 5d ago First seen · 94 lines · 34 tokens per session scan A b35e9eaf8056

Subscribe to this mod's changes

root-cause-investigator is an agent published in the GitHub repository revfactory/harness-100 (1,260 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 907 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.