five-whys

five-whys is a skill for Claude Code from tonydzi/second-brain-starter-kit. It costs 87 tokens per session (3,272 once invoked), scanned A, original, MIT.

A root-cause investigation method that asks why a recurring defect keeps happening across several cases. Root cause means the underlying problem rather than the immediate symptom.

In plain words
What is it for?
Use it to investigate a repeated software or operational defect and identify the condition that needs fixing.
Why use it?
It prevents treating repeated failures as unrelated incidents or inventing an explanation for a single event. It is intended for a pattern of recurrence, not an isolated failure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; $skill-name invocation.

Part of the second-brain-skills plugin — 246 skills shipped together

Good fit Use it to investigate a repeated software or operational defect and identify the condition that needs fixing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tonydzi/second-brain-starter-kit/five-whys
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 tonydzi/second-brain-starter-kit --skill five-whys
Clone the repo
git clone --depth 1 https://github.com/tonydzi/second-brain-starter-kit

Made for: Claude Code.

Or install second-brain-skills, the plugin that ships this one along with the rest of its 246 skills.

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 five-whys

README.md
[![agentmods](https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/five-whys/github.svg)](https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/five-whys)
Your own site
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/five-whys"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/five-whys/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 five-whys

Your own site · 80×15
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/five-whys"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/five-whys.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,272 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 $0.00087 $0.03272
Opus 5.5 $0.00035 $0.01309
Sonnet 5.5 $0.00017 $0.00654
Haiku 4.5 $0.00009 $0.00327

Measured 11d ago against content hash 9b975114640a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

five-whys 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 11d 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/five-whys/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/five-whys — доказать корень по серии случаев

Это расследование причин, а не генератор объяснений и не способ немедленно придумать новый механизм. /five-hard задаёт пять трудных вопросов к убеждению; к root-cause он не относится. В Claude вызывай /five-whys, в Codex — $five-whys.

Шаг 0 — сначала дверь, затем отдельная сессия

Явные фразы Антона «а опять почему?», «пять почему» и «чини корень» активируют этот гейт, но не разрешают выдумать серию или причину. Обычный автоматический вход — 3-й датированный случай одной смысловой семьи. Не считай по тексту ошибки или случайно придуманному имени класса.

До выбора --class выполни:

python "$HOME/.claude/scripts/prior_art.py" class "<нейтральное описание поломки>"

exit 0 означает, что прежнее не найдено; exit 3 означает найденный prior art, а не ошибку. Если прибор напечатал СЕМЬЯ <slug>, используй этот slug. Если известной семьи нет, но прибор показал прежние строки, бери имя предмета ремонта/нарушенного инварианта из самой ранней совпавшей строки. При exit 0, когда прежней строки нет, назови класс по текущему предмету ремонта/нарушенному инварианту и запиши его как 1-й датированный случай. Канал, код возврата, текст алерта и симптом классом не являются. Новая семья и сама причина — claims: не канонизируй их без улики.

Если текущий случай ещё не записан, запиши его только через дверь:

python "$HOME/.claude/scripts/selfheal.py" journal --class <семья> --what "<что>" --conditions "<условия>" --parts "<сопричастные>" --guess "🤔 <гипотеза>"

Не используй journal --dry-run: у этой команды dry-run не является безопасной гарантией. Счёт бери из фактического ответа selfheal.py; дедуп с ненулевым кодом означает, что новая датированная строка не появилась.

Полный разбор разрешён, если выполнено хотя бы одно условие:

  • есть три отдельные датированные строки одной смысловой семьи;
  • немедленный carve-out: безопасность, потеря данных, деньги, RED KEEP-ядро (sync, бэкапы, секреты, QQQ, рельсы наружу, deadman) или соврал сам прибор;
  • Антон явно потребовал разбор системного класса и дал серию; его приказ открывает дверь расследования, но количество случаев и доказанность всё равно называются честно.

Read the full file on GitHub · 201 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. 11d ago Changed · -2 lines 9b975114640a
  2. 16d ago Changed · +15 lines · +12 tokens per session 19a978d62a3b
  3. 25d ago First seen · 188 lines · 75 tokens per session scan A b50def01287f

Subscribe to this mod's changes

five-whys is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 3,272 once invoked, about $0.0003 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 2026-09-24.

Related

Other skills, from other repositories

wiki-lint

Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…

AgriciDaniel/claude-obsidian · 79 tokens

defuddle

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

AgriciDaniel/claude-obsidian · 57 tokens

wiki-fold

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…

AgriciDaniel/claude-obsidian · 76 tokens

wiki-query

Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…

AgriciDaniel/claude-obsidian · 75 tokens

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…

AgriciDaniel/claude-obsidian · 84 tokens