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 agentmods add skills/peterfei/forge-skill/kaizen-skillnpx skills add peterfei/forge-skill --skill kaizen-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/kaizen-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/kaizen-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/kaizen-skill.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.02781 |
| Opus 5 | $0.00043 | $0.01391 |
| Sonnet 5 | $0.00017 | $0.00556 |
| Haiku 4.5 | $0.00009 | $0.00278 |
Grade A, and why
kaizen-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 4d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
改善（Kaizen）· 思维工具
"Kaizen means improvement. Moreover, it means continuing improvement in personal life, home life, social life, and working life." — Masaaki Imai
激活条件与触发词
- 直接调用：「用改善/Kaizen分析...」「持续改进建议」
- 语义触发：用户提到效率低、质量不稳定、流程冗长、想渐进优化
- 组合调用：「先用改善找优化点，再用系统思维看整体结构」
方法框架概览
改善的核心是通过小步快跑的渐进式优化累积大变革，它通过现场主义看到真实问题、标准化奠基底、消除七种浪费来让任何人都有能力持续贡献改善。
核心原理（3-7个，每个须附 ≥2 个跨域证据）
原理 1: 小步改进累积为大变革
一句话定义：每天进步 1%，一年后强大 37 倍。
跨域证据：
- 汽车制造：Toyota 每年收到百万条员工改善建议，人均年几十条建议，持续累积成 TPS（来源：Liker, The Toyota Way, 2004）
- 动画制作：Pixar 每日站会(Dailies)每个人都可以提改进建议，每部电影迭代数百次（来源：Catmull, Creativity Inc., 2014）
应用方式：不是制定完美的改进计划，而是今天就开始做一件能改善的小事。记录每天做了什么改善。
局限：小步改善对需要根本性突破的场景不够。结构性问题需要系统变革而非增量改善。
原理 2: 现场主义 — 到现场看到真实问题
一句话定义：在办公桌上看数据看不到真正的问题。走到问题发生的现场去。
跨域证据：
- 汽车制造：Toyota 管理层被要求每周"站在生产线上观察 4 小时"（来源：Ohno, Toyota Production System, 1988）
- 科技管理：Amazon Bezos 坚持定期到仓库一线工作，发现配送痛点（来源：Stone, The Everything Store, 2013）
应用方式：直接去看问题发生的现场——生产线、客服电话录音、用户使用产品时的屏幕录制，而不是看 PPT 报告。
局限：现场观察是抽样式的，需要与规模化数据结合判断。
原理 3: 标准化是改善的基石
一句话定义：没有标准就没有改善——如果每次做法不一样，你无法判断"改进"是真的改进还是随机波动。
跨域证据：
- 餐饮：McDonald's 的标准化操作流程使全球每家店做出一致的汉堡，然后在此标准上迭代优化（来源：Love, McDonald's: Behind the Arches, 1986）
- 软件开发：CI/CD 标准化流程使团队能衡量每次部署速度和质量，在此基础上持续改善（来源：Forsgren, Humble, Kim, Accelerate, 2018）
应用方式：先把当前流程写下来（即使它不完美），这是改善的起点。然后问：哪一步最慢？哪步最容易出错？
局限：过度标准化可能扼杀创造力和灵活性。标准化适用于重复性流程，不适用于创意工作。
原理 4: 消除浪费（Muda）是核心目标
一句话定义：任何不增加客户价值的活动都是浪费。
跨域证据：
- 制造业：Toyota 识别 7 种浪费：过度生产、等待、运输、过度加工、库存、动作、缺陷（来源：Ohno, Toyota Production System, 1988）
- 软件开发：Lean Software Development 将 7 种浪费翻译为软件语境：未完成的功能、等待批准、手工作业等（来源：Poppendieck, Lean Software Development, 2003）
应用方式：列出一天中做的所有事，逐个问"用户或客户会为这个付钱吗？"如果不会——这是浪费，想办法消除或减少。
局限：某些"不直接增加客户价值"的活动是必需的（如合规检查、安全测试）。不是所有非增值活动都是可消除的浪费。
操作协议（Agentic Protocol）
Step 1: 问题分类
适用信号：
- 重复性流程的效率和质量问题
- 团队持续感到效率低但不知道从哪改
- 想要建立改善文化但不知从何开始
不适用信号：
- 需要根本性的商业模式变革（改善是渐进的）
- 创意工作流程的"效率"问题（创意难以标准化）
- 紧急危机需要快速解决方案
Step 2: 改善式分析
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.
- 4d ago First seen · 182 lines · 85 tokens per session scan A 8f5d5b088b21
kaizen-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 2,781 once invoked, about $0.0004 per session on Opus 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
descend
Verifies whether the problem was correctly identified before solving, auditing pattern matches against first principles.
fundraising-narrative
This skill should be used when the user asks about "pitch deck", "fundraising story", "investor pitch", "VC narrative", "pitch narrative", "fundraising deck", "pitch structure", "Sequoia format", "why now slide", "market size slide", "TAM SAM SOM", "earned secret", "value hypothesis", "product-market fit"…
investor-relations
This skill should be used when the user asks about "investor update", "board deck", "board meeting", "investor communication", "monthly update", "quarterly update", "investor email", "bad news investors", "pivot communication", "crisis communication investors", "investor ask", "warm intro", "VC relationship"…
ux-principles
User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.