cynefin-skill

cynefin-skill is a skill for Claude Code, Codex from peterfei/forge-skill. It costs 87 tokens per session (7,048 once invoked), scanned A, original, MIT.

A decision framework for sorting situations into five types based on how clear their cause-and-effect relationships are, from obvious to chaotic.

In plain words
What is it for?
Use it to classify a problem, choose whether to follow established practice, seek expert analysis, or run experiments, and adjust as conditions change.
Why use it?
It helps prevent treating an uncertain or changing situation like a routine problem with a known answer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to classify a problem, choose whether to follow established practice, seek expert analysis, or run experiments, and adjust as conditions change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/peterfei/forge-skill/cynefin-skill
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 peterfei/forge-skill --skill cynefin-skill
Clone the repo
git clone --depth 1 https://github.com/peterfei/forge-skill

Made for: Claude Code, Codex.

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 cynefin-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/peterfei/forge-skill/cynefin-skill/github.svg)](https://agentmods.dev/skills/peterfei/forge-skill/cynefin-skill)
Your own site
<a href="https://agentmods.dev/skills/peterfei/forge-skill/cynefin-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/cynefin-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.

agentmods 80×15 button for cynefin-skill

Your own site · 80×15
<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="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 7,048 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 $0.07048
Opus 5.5 $0.00035 $0.02819
Sonnet 5.5 $0.00017 $0.01410
Haiku 4.5 $0.00009 $0.00705

Measured 2mo ago against content hash 7ac06962d6f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

methods/cynefin-skill/SKILL.md · 245 lines

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:

  1. 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)
  2. 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:

  1. 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)
  2. 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)。

Read the full file on GitHub · 245 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. 2mo ago First seen · 245 lines · 87 tokens per session scan A 7ac06962d6f8

Subscribe to this mod's changes

cynefin-skill is a skill published in the GitHub repository peterfei/forge-skill (15 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 7,048 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 2026-08-30.