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.
npx skills add orlando-japan/claude-code-setting --skill root-cause-analysisgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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.
[](https://agentmods.dev/skills/orlando-japan/claude-code-setting/root-cause-analysis)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/root-cause-analysis"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/root-cause-analysis/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.
<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/root-cause-analysis"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/root-cause-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.01068 |
| Opus 5.5 | $0.00015 | $0.00427 |
| Sonnet 5.5 | $0.00008 | $0.00214 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
root-cause-analysis 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root cause analysis
A symptom is what you see. A cause is what produced it. Fixing the symptom stops the pain now; fixing the cause stops the pain forever.
The 5 Whys
The simplest tool: ask "why" until you hit a cause you can act on at the system level, not the code level.
Example:
- Symptom: the checkout page returned 500 errors at 3pm.
- Why? → The
paymentservice threw an unhandled exception. - Why? → It received a null value for
user.address. - Why? → The
userservice returned a user with no address field. - Why? → The migration that added
addressonly ran for new users; old users had no address. - Why? → The migration didn't include a backfill step for existing rows.
Stop condition reached: "We don't enforce backfill as part of migration review." That's actionable at the system level — write a checklist, add a lint, add the review rule. Fixing at this level prevents the next null pointer.
Going further ("why don't we have a checklist?" → "we never thought of it") doesn't help. You've hit the useful floor.
Guardrails on 5 Whys
- Stop at a cause you can act on. Not "a human made a mistake." "A human made a mistake" is never a root cause — it's where to start asking why the system permitted the mistake.
- Don't stop at "bad code." Bad code got merged, that's a process question. Why did review not catch it? Why did tests not catch it?
- One "why" per step. Don't branch mid-sequence. If there are two causes, analyze them separately.
- Follow causal chains, not correlations. "Shipped Tuesday, broke Tuesday" is correlation. Prove causation.
Causes come in layers
For most incidents, you'll find multiple layers of cause:
- Technical cause. Null pointer, race, config mistake.
- Process cause. Code review missed it, test wasn't in the suite, deploy policy let it through.
- Organizational cause. No owner for this service, pressure to ship, stale on-call rotation.
A good RCA addresses at least two layers. A great one addresses all three. Fixing only the technical cause guarantees a next incident with a different technical symptom and the same process gap.
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.
- 1mo ago First seen · 105 lines · 38 tokens per session scan A a44272bab78a
root-cause-analysis is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,068 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
huawei-cloud-cdn-abnormal-status-code-analysis
Diagnose CDN business abnormal HTTP status codes (4xx/5xx) using hcloud CLI. Discover and quantify 4xx/5xx volume, localize the exact status code and time window, fork edge-generated vs origin-generated via back-to-source status statistics, correlate top-N distribution, narrow root cause on CDN edge config or origin…
huawei-cloud-agentarts-obs-diagnosis
Observability no-data diagnosis skill for Huawei Cloud AgentArts agent-ops platform. Systematically diagnoses missing metrics, logs, and traces/sessions in agent-ops by checking subscription metadata, data pipeline (APM/AOM/LTS), query parameters, and authentication. Generates root-cause analysis and fix…
apex-diagnose
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent…
fixing
Diagnose why a PR's CI failed — compare the CI definition against the sandbox, classify the failure, and make the minimal repair. Use when a PR is red and you must work out why before changing anything.
huawei-cloud-cdn-dns-resolution-diagnosis
Diagnose CDN domain DNS resolution issues using hcloud CLI and Python DNS probes. Query the CDN domain detail to obtain the expected CNAME, probe the actual DNS resolution of the domain via scripts/dnsresolve.py (dnspython) to collect resolved IP addresses, and verify the IP attribution against Huawei Cloud CDN via…