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 marcos-sponton/frameworks-as-skills --skill cynefingit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-skillsWrote 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/marcos-sponton/frameworks-as-skills/cynefin)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/cynefin"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/cynefin/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/marcos-sponton/frameworks-as-skills/cynefin"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/cynefin.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 | $0.00254 | $0.02641 |
| Opus 5 | $0.00127 | $0.01321 |
| Sonnet 5 | $0.00051 | $0.00528 |
| Haiku 4.5 | $0.00025 | $0.00264 |
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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cynefin
Dave Snowden's sense-making framework for deciding what kind of problem you actually have — before you reach for a method. Distilled from the 2003 IBM Systems Journal paper (Kurtz & Snowden), the 2007 HBR A Leader's Framework for Decision Making (Snowden & Boone), and 20+ years of subsequent refinements — the 2014 renamings (Simple → Obvious → Clear), the 2017 introduction of liminal zones, the 2019–2020 Aporetic Turn, Estuarine Mapping (formalized 2023–2024), and near-daily posts on thecynefin.co/author/dave-snowden and the cynefin.io wiki.
This skill helps you sense-make into Cynefin, not sort projects into it. Cynefin is not a 2×2. It is not a categorization tool. It is a framework for contextualizing a situation so you don't apply Complicated methods to Complex problems, or extract "best practice" from a success that only worked because of context you didn't see.
When this skill activates
Use this skill when the user is:
- Deciding what approach to take on a messy, ambiguous, or novel situation.
- Running a post-mortem on a strategy, launch, roadmap, or pilot that didn't behave as expected.
- Defaulting to "best practice" for a problem that isn't routine.
- Reaching for SAFe / Scaled Agile / Design Thinking / Systems Thinking / Lean Startup without asking whether the domain fits.
- Trying to extract a repeatable playbook from a one-off success.
- Designing a pilot — especially if they're planning "the pilot" (singular).
- Facing genuine "we don't know what we don't know" territory.
- Managing crisis / turnaround / high-uncertainty operations.
- Deciding when experts help vs. when experiments help.
Do NOT use this skill when:
- The user has a genuinely routine operational task in the Clear domain (invoice processing, hand-luggage rules). Cynefin's answer there is "use best practice" — the framework is overkill.
- The user asks for a diagrammatic summary of Cynefin. Give them the cynefin.io wiki and the Snowden & Boone HBR paper and don't run the framework.
- The user wants Cynefin as a project-sorting tool. Push back: it isn't one. Offer sense-making instead.
- The user is looking for a competitive-choice framework — that's Playing to Win or Rumelt's kernel, not Cynefin.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 7.0 KB
- README.md 7.0 KB
- references/applications.md 12 KB
- references/author-live-sources.md 9.8 KB
- references/examples.md 13 KB
- references/heuristics.md 19 KB
- references/method.md 14 KB
- references/post-book.md 17 KB
- references/prompts.md 7.7 KB
- references/sources.md 7.2 KB
- references/voice-and-tone.md 17 KB
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.
- 11d ago First seen · 97 lines · 254 tokens per session scan A a0a0d53da3f7
cynefin is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 254 tokens to every session and 2,641 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.