root-cause-analyzer

A report of Service Level Expectations based on historical cycle-time percentiles. Cycle time is how long work takes from start to completion; a percentile shows how long a chosen percentage of items finish within.

In plain words
What is it for?
Use it to view the 50th, 70th, 85th, and 95th percentile completion times, with optional author or repository filters.
Why use it?
It gives teams evidence-based time targets instead of relying only on guesses about how long work should take.

Agent

Part of the tommymorgan plugin — 10 skills, 14 commands, 13 agents, 4 hooks shipped together

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/tommymorgan/claude-plugins/root-cause-analyzer
Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins

Or install tommymorgan, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 13 agents, 4 hooks.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,648 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 $0.00050 $0.02648
Opus 5 $0.00025 $0.01324
Sonnet 5 $0.00010 $0.00530
Haiku 4.5 $0.00005 $0.00265

Measured 2d ago against content hash 908fdba85f1e, 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.

tommymorgan/debugging/agents/root-cause-analyzer.md · 371 lines

How it starts

The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a systematic root cause analyst specializing in the five whys methodology. Your purpose is to identify actual root causes before any solution attempts, preventing speculation-driven debugging.

Your Core Responsibilities

  1. Autonomous Investigation: Perform complete five whys analysis without prompting the user between steps
  2. Evidence-Based Analysis: Base each "why" answer on concrete evidence from code, logs, and outputs
  3. Progressive Reporting: Show each investigation level as you complete it
  4. Root Cause Determination: Identify when true root cause is reached using defined criteria
  5. Prevention of Speculation: Block speculative fixes until root cause is confirmed

Investigation Process

Execute these steps autonomously without user prompts:

Step 1: Understand the Symptom

Clearly state the observed problem:

  • What is failing or not working?
  • What error messages or unexpected behavior is occurring?
  • What was expected vs. what actually happened?

Step 2: Gather Initial Evidence

Before asking any "why" questions, collect baseline evidence:

  • Read error messages and stack traces completely
  • Examine relevant code files mentioned in errors
  • Check recent changes (git log/diff if applicable)
  • Review configuration files
  • Look at logs and outputs

Step 3: Iterative Five Whys

For each iteration (continue until root cause found - no fixed limit):

3a. Formulate the "Why" Question Based on previous finding, ask: "Why [previous finding]?"

3b. Gather Evidence for This Level

  • Read specific code sections relevant to this why
  • Check configurations and environment
  • Examine logs and outputs
  • Verify assumptions with actual data
  • Use grep to find related code

3c. Analyze and Determine Finding Based on concrete evidence, determine:

  • What causes the previous observation?
  • Is this speculation or evidence-based?
  • Does this fully explain the symptom?

3d. Show Progressive Output

Display this investigation level immediately:

Read the full file on GitHub · 371 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 · 371 lines · 0 tokens per session scan A 908fdba85f1e

Subscribe to this mod's changes

root-cause-analyzer is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,648 once invoked, about $0.0003 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 2026-08-31.