A step-by-step method for finding the real cause of a software problem before changing code. It uses error evidence, traces incorrect values back to their source, compares working and failing cases, and tests one explanation at a time.

Use it to investigate a failing test, production bug, unexpected result, performance issue, build failure, or integration that does not work.

It reduces guesswork and fixes symptoms that may otherwise return in another place. It is intended for failures, bugs, surprising behaviour, slow performance, broken builds, and integration problems.

root-cause — Skill for Claude Code by hamr0

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.

Any agent

npx skills add hamr0/agentic-toolkit --skill root-cause

Clone the repo

git clone --depth 1 https://github.com/hamr0/agentic-toolkit

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hamr0/agentic-toolkit/root-cause/github.svg)](https://agentmods.dev/skills/hamr0/agentic-toolkit/root-cause)

Your own site

<a href="https://agentmods.dev/skills/hamr0/agentic-toolkit/root-cause"><img src="https://agentmods.dev/badge/skills/hamr0/agentic-toolkit/root-cause/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hamr0/agentic-toolkit/root-cause"><img src="https://agentmods.dev/badge/skills/hamr0/agentic-toolkit/root-cause.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,058 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.02058
Opus 5	$0.00028	$0.01029
Sonnet 5	$0.00011	$0.00412
Haiku 4.5	$0.00006	$0.00206

Measured 3d ago against content hash 1413fbc3e619, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

root-cause 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (find-polluter.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to root-cause — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

ai/subagentic/ampcode/skills/root-cause/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Root Cause

Find the cause before you change any code.

The Law

NO FIX WITHOUT A CAUSE YOU CAN POINT AT

A fix at the place the error appeared is a symptom fix. It is a failure even when the symptom goes away, because the real cause is still there and will surface somewhere else, later, with less context.

You cannot propose a fix until Phase 1 is done.

When to Use

Any technical issue: a failing test, a production bug, unexpected behaviour, a performance problem, a broken build, an integration that will not talk.

Especially when it feels like overkill:

Under time pressure — emergencies are exactly when guessing is most tempting and most expensive
"Just one quick fix" looks obvious
You have already tried a fix and it did not work
You do not fully understand the issue

Simple bugs have root causes too, and finding one takes minutes. Guess-and-check takes hours and leaves damage behind.

Phase 1 — Gather Evidence

Do all of this before forming any opinion about the fix.

1. Read the error completely

Do not skim past it. Read the whole message, the whole stack trace, every warning above it. Note line numbers, file paths, error codes. The answer is often written there in full.

2. Reproduce it consistently

Can you trigger it on demand? What are the exact steps? Does it happen every time?

If it is not reproducible, gather more data. Do not start guessing — an intermittent bug you cannot trigger is a bug you cannot prove you fixed.

3. Check what changed

Recent commits, the working diff, new dependencies, config edits, environment differences between the place it works and the place it does not.

Be careful here: the most recent change is the most available suspect, not the most likely one. Recency is a lead to test, never a conclusion.

4. Instrument the boundaries (multi-component systems)

When the path crosses components — CI → build → sign, API → service → database, workflow → script → tool — do not reason about where it breaks. Measure it.

Read the full file on GitHub · 221 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

find-polluter.sh 1.5 KB runs code

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.

3d ago First seen · 221 lines · 56 tokens per session scan A 1413fbc3e619

Subscribe to this mod's changes

root-cause is a skill published in the GitHub repository hamr0/agentic-toolkit (22 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 2,058 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to root-cause, differing in 0 lines, and is treated as a copy.

Debugging agent ai automation developer-tools workflow

triage

Verify an open GitHub issue or PR against the current code and decide its fate: implement, keep, or close with a factual comment. Use when the user asks to triage, verify, check, handle, or clean up an issue, a PR, or the tracker.

bengous/claude-code-plugins · 59 tokens

null-as-error-cc

Audit an Effect codebase for silent error swallowing -- catchAll patterns that collapse errors into sentinel values (null, [], false, void) in the success channel. Runs a scanner script, spawns a read-only auditor, and produces a classified report. NOT for: non-Effect projects, React/frontend code, plain TypeScript…

bengous/claude-code-plugins · 74 tokens

root-cause