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 peterfei/forge-skill --skill five-whys-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWrote 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/peterfei/forge-skill/five-whys-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/five-whys-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/five-whys-skill/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/peterfei/forge-skill/five-whys-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/five-whys-skill.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 | $0.00089 | $0.05724 |
| Opus 5.5 | $0.00036 | $0.02290 |
| Sonnet 5.5 | $0.00018 | $0.01145 |
| Haiku 4.5 | $0.00009 | $0.00572 |
Grade A, and why
five-whys-skill 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
五个为什么(5 Whys)· 思维工具
"重复问五次'为什么',你就会找到问题的根本原因。" —— 大野耐一(Taiichi Ohno),《丰田生产方式》,1978
激活条件与触发词
- 直接调用:「用五个为什么分析...」「5 Whys这个故障」「五问法追查根因」
- 语义触发:用户面对一个具体问题/故障/事故,想知道"为什么会发生",希望找到根本原因而非仅处理表面症状
- 组合调用:「先用鱼骨图梳理可能原因,再用五个为什么深挖根因」「先用五个为什么定位根因,再用 PDCA 制定改善计划」
方法框架概览
五个为什么的核心是通过连续追问"为什么"穿透表面症状直抵系统性根因,它通过 5 个原理来将模糊的问题转化为可行动的根本解决方案。
核心原理(3-7个,每个须附 ≥2 个跨域证据)
原理 1: 因果链的深度穿透——症状与根因之间存在多层因果关系
一句话定义:每一个可见的问题背后,都有一连串未被审视的因果链条,直到抵达系统性的根本原因。
跨域证据:
- 制造业(丰田):大野耐一的经典案例——机器停机,表面原因是保险丝熔断,逐层追问后发现根因是油泵没有过滤网导致金属碎屑进入泵轴(来源:Ohno, Toyota Production System: Beyond Large-Scale Production, 1978)
- 航空安全:NASA 在事故调查政策 NPR 8621.1 中明确规定,根因分析必须追问"为什么"直至识别出所有系统性贡献因素,而非停留在直接原因(来源:NASA, NPR 8621.1 NASA Procedural Requirements for Mishap Investigation, Appendix I)
应用方式:面对任何故障或问题,不要在第一个答案处停下来,至少追问 3 层以上,直到触及"可以通过改变流程/系统来永久解决"的层面。
局限:因果链条并非总是线性的,复杂问题可能有多条因果分支交汇于不同节点。
原理 2: "五"是指导而非教条——追问深度取决于问题的复杂度
一句话定义:追问的次数不必须恰好五次,关键在于穿透到可采取系统性行动的层面。
跨域证据:
- 精益管理:大野耐一本人从未硬性规定"恰好五次"。Lean Blog 的分析指出,大野耐一经典案例中实际追问了七层才抵达真正的系统性根因(来源:Lean Blog, "Even Ohno's Classic 5 Whys Example Deserves Another Why", 2026)
- 软件工程:Google SRE 团队在故障复盘(Postmortem)中不限定追问次数,而是追问到"我们能改变什么系统来防止再次发生"为止(来源:Google SRE Book, Blameless Postmortem for System Resilience, 2016)
应用方式:以"是否已经到达一个可以设计系统性对策的原因"作为停止条件,而非机械地数到五。
局限:对于缺乏经验的执行者,"五次"作为硬性规则仍有其训练价值,避免追问过浅。
原理 3: 根因往往指向系统和流程,而非个人
一句话定义:连续追问会自然地将责任从"谁犯了错"转移到"什么系统允许这个错误发生"。
跨域证据:
- 互联网/电商:2004 年 Jeff Bezos 在亚马逊仓库亲自主持 5 Whys 分析,一名工人在传送带上夹伤手指,逐层追问后根因指向预算约束导致的编制不足和培训缺失,而非工人个人的疏忽(来源:Brad Stone, The Everything Store, 2013)
- 创业管理:Eric Ries 在《精益创业》中强调"每一个看似技术问题的根因都是一个人的问题",5 Whys 应用于组织流程改进而非追责个人(来源:Eric Ries, The Lean Startup, 2011; Eric Ries, "The Five Whys for Start-ups", HBR, 2010)
应用方式:在每一层追问时,如果答案是"某人犯了错",继续追问"为什么系统允许这个错误发生",直到找出流程/制度/工具层面的改进点。
局限:在某些场景下(如蓄意破坏、严重渎职),个人责任确实是根因,强行转向系统可能掩盖真正的责任问题。
原理 4: 追问质量取决于提问者的领域知识
一句话定义:同样的问题,不同知识背景的人会构建出不同的因果链条,抵达不同的"根因"。
跨域证据:
- 可靠性工程:Mark Galley(ThinkReliability 创始人)指出 5 Whys 的最大弱点之一是"受限于调查者的知识面"——同一事件由不同人分析会得出不同的根因,缺乏可重复性(来源:Mark Galley, "Top Criticisms of the 5-Why Approach...and What the Critics Don't Understand", LinkedIn/ThinkReliability)
- 医疗安全:美国医疗机构评审联合委员会(The Joint Commission)在根因分析框架中强调,RCA 团队必须包含多学科成员,单一视角的分析会导致根因遗漏(来源:The Joint Commission, Framework for Conducting a Root Cause Analysis and Action Plan; AHRQ Patient Safety Network, Root Cause Analysis Primer)
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 · 249 lines · 89 tokens per session scan A 3f0019b06ec8
five-whys-skill is a skill published in the GitHub repository peterfei/forge-skill (15 stars, last pushed 3mo ago), licensed MIT. It adds 89 tokens to every session and 5,724 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
mcpls
Install, configure, and run the mcpls CLI — a Rust binary bridging MCP to LSP that gives an agent compiler-grade code intelligence (hover, definitions, references, diagnostics, rename). Use when setting up or registering mcpls as an MCP server, writing or debugging an mcpls.toml, choosing CLI flags or MCPLS…
patch-edit
Apply one rewrite-plan step at a time as small reviewable file edits, never rewriting whole files when a localised change suffices.
od-code-migration
Default reference pipeline for the code-migration taskKind — code-import → design-extract → token-map → rewrite-plan → patch-edit ↔ build-test devloop → diff-review → handoff.
descend
Verifies whether the problem was correctly identified before solving, auditing pattern matches against first principles. Now with mathematical depth metrics, recursive audit, cognitive traces, and verification gates.
module-federation
Add, review, or debug client-rendered Module Federation support in Rsbuild-first TypeScript applications. Covers host/remote roles, exposes, remotes, shared dependencies, generated types, runtime loading failures, and observability checks.