rootcause-rca

A structured workflow for root-cause analysis (RCA), the process of finding why an incident happened. It gathers evidence, builds a timeline, drafts the analysis, plans fixes, and exports a postmortem report.

In plain words
What is it for?
Use it for outage investigations, change-before-failure analysis, remediation plans, corrective and preventive actions, and postmortem documents.
Why use it?
It turns scattered incident information into a documented explanation of what happened and how to prevent a repeat.

Skill for Claude CodeCodex

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 skills/yindia/rootcause/rootcause-rca
Any agent
npx skills add yindia/rootcause --skill rootcause-rca
Clone the repo
git clone --depth 1 https://github.com/yindia/rootcause

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,671 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 $0.01671
Opus 5 $0.00000 $0.00835
Sonnet 5 $0.00000 $0.00334
Haiku 4.5 $0.00000 $0.00167

Measured 3d ago against content hash f5033fa10bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rootcause-rca 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.

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.

skills/claude/rootcause-rca/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: rootcause-rca

Full incident RCA pipeline for evidence collection, timeline analysis, root-cause drafting, remediation planning, and postmortem export.

This skill is for structured incident documentation and decision support, not for ad-hoc single-command troubleshooting.

Trigger Phrases

Use this skill when the user asks for:

  • root cause analysis
  • incident report
  • postmortem draft
  • what changed before outage
  • remediation plan
  • corrective and preventive actions
  • timeline export

RootCause Tools Allowed

Only use these tool names in this skill:

  • rootcause.incident_bundle
  • rootcause.change_timeline
  • rootcause.rca_generate
  • rootcause.remediation_playbook
  • rootcause.postmortem_export
  • k8s.events_timeline
  • helm.list

RCA Pipeline Overview

Canonical sequence:

  1. Bundle
  2. Timeline
  3. RCA draft
  4. Remediation playbook
  5. Postmortem export

Shorthand: bundle -> timeline -> rca -> remediation -> postmortem

Step 1: Incident Bundle

Use rootcause.incident_bundle to gather cross-tool evidence.

Recommended minimal parameters:

namespace: payments
keyword: "timeout"
includeHelm: true
includeDefaultChain: true

Useful optional parameters:

  • eventLimit: tune for noisy namespaces.
  • maxSteps: cap diagnostic expansion.
  • outputMode: bundle for full context, timeline for condensed view.
  • continueOnError: keep collecting when one branch fails.

When to run again:

  • evidence is too generic,
  • namespace was too broad,
  • keyword was not specific.

Step 2: Change Timeline

Use rootcause.change_timeline to align cluster events and release changes.

Recommended parameters:

namespace: payments
keyword: "timeout"
includeHelm: true
includeNormal: false
timelineLimit: 150

Use timeline to answer:

  • What changed just before impact?
  • Was there a rollout, config update, or restart wave?
  • Did warning events precede customer-visible failure?

If Helm activity is expected but absent:

  1. run helm.list in relevant namespace,
  2. confirm release names and history context.

Read the full file on GitHub · 260 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. 3d ago First seen · 260 lines · 0 tokens per session scan A f5033fa10bad

Subscribe to this mod's changes

rootcause-rca is a skill published in the GitHub repository yindia/rootcause (42 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,671 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.