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/cynefin-skillnpx skills add peterfei/forge-skill --skill cynefin-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/cynefin-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/cynefin-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/cynefin-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 5.1 | $0.00087 | $0.07048 |
| Opus 5 | $0.00044 | $0.03524 |
| Sonnet 5 | $0.00017 | $0.01410 |
| Haiku 4.5 | $0.00009 | $0.00705 |
Grade A, and why
cynefin-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 6d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cynefin 框架 · 思维工具
"The framework is designed to help decision makers understand that there are different types of systems, and each requires a different type of decision-making and sense-making process." -- David J. Snowden, Cynefin: A Sense-Making Framework (2010)
激活条件与触发词
- 直接调用:「用 Cynefin 框架分析...」「用 5 域分类...」「把这个问题放进 Cynefin...」
- 语义触发:用户面对不确定性问题,不确定该「分析」还是「实验」;用户将复杂社会问题当作工程问题处理;用户使用了大量最佳实践但效果不佳
- 组合调用:「先用 Cynefin 分类问题域,再选对应方法」;「Cynefin 分类 + 系统思维分析」
方法框架概览
Cynefin 框架的核心是将问题按因果清晰度分为 5 个域(清晰/繁杂/复杂/混沌/失序),每个域有不同的因果结构和对应的决策策略。它不是一个分类标签工具,而是一个要求持续「意义建构」(sense-making)的动态框架,旨在防止将复杂问题误当作繁杂问题处理的灾难性失败。
核心原理(3-7个,每个须附 ≥2 个跨域证据)
原理 1: 5 域分类 —— 不同问题域有本质不同的因果结构
一句话定义:问题不是同一个量级的——有的因果关系直观可见(清晰域),有的需要专家分析(繁杂域),有的只能事后回溯(复杂域),有的根本不存在可辨识的因果(混沌域),有的你甚至不知道是哪一类(失序域)。
跨域证据:
- 公共卫生领域:普通的流感诊断(清晰域——已知症状对应已知疗法)与 COVID-19 初期应对(复杂域——未知传播机制、未知致死率、未知有效干预)是本质不同的决策情境。将 COVID 早期当作繁杂域(召集专家组制定方案然后执行)导致了多国第一波防控失败。来源:Snowden, "Managing Complexity (and Chaos) in Times of Crisis," EU Commission Joint Research Centre (2020)
- 软件开发领域:为已知需求做一个标准的 CRUD 后台(清晰域——已有成熟的框架和模式)vs. 从零构建一个无先例的 AI 产品(复杂域——用户会怎么用不可预知)需要完全不同的组织方式。前者适合 Waterfall/Plan-driven,后者必须 Agile/Probe-driven。来源:Kurtz & Snowden, "The New Dynamics of Strategy," IBM Systems Journal (2003)
应用方式:面对任何问题时,首先判断其因果清晰度——已知的因果关系有多少?这些关系是稳定的还是变化的?是否存在「答案在行动中涌现」的特征?
局限:同一个问题在不同层次(个体/组织/社会)可能落在不同域,需要明确分析的层次和边界。
原理 2: 有序域逻辑 —— 清晰域与繁杂域使用「感知-分类/分析-响应」
一句话定义:在因果清晰的有序域中,正确的方法是先收集信息(感知),然后根据信息匹配已知框架或进行专家分析(分类/分析),最后执行确定的方案(响应)。这两个域共享「因果先行」的前提,区别在于是否需要专家介入。
跨域证据:
- 金融风控领域:信用卡反欺诈系统(繁杂域)——系统感知交易模式,专家/模型分析异常信号,然后做出拦截决策。这是一个感知-分析-响应的典型循环。来源:Bolton & Hand, "Statistical Fraud Detection: A Review," Statistical Science (2002)
- 军事后勤领域:标准弹药补给(清晰域)——感知弹药存量,按标准分类属于「低-中-高-紧急」哪一级,按既定 SOP 响应补充。不需要分析,只需要分类。来源:Van Creveld, M., Supplying War: Logistics from Wallenstein to Patton (1977),展示标准补给流程与战场不确定性的对比
应用方式:判断问题是清晰还是繁杂的关键是——这个问题有无已知的良好实践(Good Practice)还是只有最佳实践(Best Practice)?清晰域适用良好实践(可标准化的),繁杂域需要最佳实践(依赖专家判断的)。
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.
- 6d ago First seen · 245 lines · 87 tokens per session scan A 7ac06962d6f8
cynefin-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 7,048 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.
specification-writing
Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.