cynefin

cynefin is a command for Claude Code from neurofoo/agent-skills. It costs 0 tokens per session (929 once invoked), scanned A, original, MIT.

An analysis using Cynefin, a framework for matching the way you respond to the kind of situation you face. It distinguishes clear, expert-dependent, unpredictable, crisis, and unclear situations.

In plain words
What is it for?
Use it to assess projects, incidents, decisions, or other situations where the appropriate problem-solving approach is uncertain.
Why use it?
It helps teams choose between following a known practice, consulting experts, experimenting, or stabilizing a crisis.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the thinking-frameworks plugin — 8 skills, 8 commands shipped together

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.

agentmods
npx agentmods add commands/neurofoo/agent-skills/cynefin
Clone the repo
git clone --depth 1 https://github.com/neurofoo/agent-skills

Made for: Claude Code.

Or install thinking-frameworks, the plugin that ships this one along with the rest of its 8 skills, 8 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/neurofoo/agent-skills/cynefin.svg)](https://agentmods.dev/commands/neurofoo/agent-skills/cynefin)
Your own site
<a href="https://agentmods.dev/commands/neurofoo/agent-skills/cynefin"><img src="https://agentmods.dev/badge/commands/neurofoo/agent-skills/cynefin.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 929 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00929
Opus 5 $0.00000 $0.00464
Sonnet 5 $0.00000 $0.00186
Haiku 4.5 $0.00000 $0.00093

Measured 6d ago against content hash 63f4d40c4b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cynefin 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.

cynefin/commands/cynefin.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cynefin Analysis

Analyze a situation through the Cynefin framework to understand what type of problem it is and choose the appropriate response.

Instructions

Determine which Cynefin domain the problem belongs to, then apply the appropriate response approach. Be willing to recognize that parts of a problem may span multiple domains.

Output Format

Situation: [What we're analyzing]


Initial Assessment

What kind of problem is this?

Characteristics Check

Characteristic Yes/No/Maybe Evidence
Cause and effect are clear and predictable
Experts can analyze and determine the answer
Outcomes can only be understood in hindsight
The situation is unstable/in crisis
We genuinely don't know what kind of problem this is

Domain Classification

Primary Domain: [Simple/Complicated/Complex/Chaotic/Confused]

Why this domain? [Reasoning for the classification]

Is this a pure domain or does it span multiple? [Assessment of whether different aspects belong to different domains]


Domain-Appropriate Response

If SIMPLE/OBVIOUS

Sense → Categorize → Respond

Best Practice to Apply: [The established, proven approach]

Implementation:

  1. [Step 1]
  2. [Step 2]
  3. [Step 3]

Risk: Don't overcomplicate this. Don't call in experts for simple problems.


If COMPLICATED

Sense → Analyze → Respond

Experts Needed: [Who has the expertise to analyze this?]

Analysis Required: [What do we need to investigate?]

Good Practice Options:

Option Expert View Trade-offs
[option] [analysis] [trade-offs]

Risk: Multiple right answers exist. Analysis paralysis is possible.


If COMPLEX

Probe → Sense → Respond

Safe-to-Fail Experiments:

Probe What We'd Learn Amplify if... Dampen if...
[experiment] [insight] [success indicators] [failure indicators]

Read the full file on GitHub · 155 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. 6d ago First seen · 155 lines · 0 tokens per session scan A 63f4d40c4b27

Subscribe to this mod's changes

cynefin is a command published in the GitHub repository neurofoo/agent-skills (111 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 929 tokens. 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.