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 product-on-purpose/thinking-framework-skills --skill think-complexity-domain-sortgit clone --depth 1 https://github.com/product-on-purpose/thinking-framework-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/product-on-purpose/thinking-framework-skills/think-complexity-domain-sort)<a href="https://agentmods.dev/skills/product-on-purpose/thinking-framework-skills/think-complexity-domain-sort"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-complexity-domain-sort/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/product-on-purpose/thinking-framework-skills/think-complexity-domain-sort"><img src="https://agentmods.dev/badge/skills/product-on-purpose/thinking-framework-skills/think-complexity-domain-sort.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 | $0.00124 | $0.01609 |
| Opus 5 | $0.00062 | $0.00805 |
| Sonnet 5 | $0.00025 | $0.00322 |
| Haiku 4.5 | $0.00012 | $0.00161 |
Grade A, and why
think-complexity-domain-sort 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complexity Domain Sort
The Complexity Domain Sort triages a situation by how knowable its causal structure is, then picks the response posture that fits: sense-categorize-respond for the clear, probe-sense-respond for the complex, and so on. It is descriptively named here; the framework it derives from is Cynefin, and its evidence is conceptual only. This skill runs the sort honestly. It leads with that caveat, then forces the one thing the bare label omits and that makes the sort worth running at all: a concrete next action tied to the domain, because saying "this is complex" is not a decision.
Before you run this: the evidence caveat
This sort is descriptively named; the framework it derives from is Cynefin, a trademark of The Cynefin Co. (Dave Snowden, 1999). Its evidence is tier C (conceptual): it is a coherent, widely taught sense-making heuristic, but no controlled study shows that classifying a problem this way improves decisions versus not classifying it. The 2021 PMC review applying it to internal-medicine diagnostic reasoning states the point plainly: the framework "is now widely used for teaching and as a simple heuristic; however, scientific proof of its validity has yet to be provided." The dominant failure mode is the cargo cult: stopping at the label ("ah, this is complex, we should probe") is satisfying to say and changes nothing. So the placement is a contested framing, not a found fact, and the deliverable is the next action it implies, not the bucket name.
When to Use
- The user asks for this complexity sort (or Cynefin) by name and you should run it honestly rather than refuse.
- A team is applying the wrong management style to the problem type (running an emergent initiative on a rigid best-practice plan, or smothering a routine task in deliberation) and naming that mismatch out loud would help.
- As a front end to picking how to act, where the value is legitimizing safe-to-fail experiments in the complex domain and flagging the confusion trap, not the five-box picture.
What ships with it
5 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.
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.
- 10d ago First seen · 74 lines · 124 tokens per session scan A 64580dbce757
think-complexity-domain-sort is a skill published in the GitHub repository product-on-purpose/thinking-framework-skills (15 stars, last pushed 24d ago), licensed Apache-2.0. It adds 124 tokens to every session and 1,609 once invoked, about $0.0006 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
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
acl-rule-analysis
Vendor-agnostic ACL and firewall rule analysis with shadowed rule detection, overly permissive rule identification, unused rule discovery, redundant rule flagging, and rule ordering optimization. Covers ACLs (Cisco/JunOS/EOS) and firewall policies (PAN-OS/FortiGate/CheckPoint).
add-analytics
Add Google Analytics 4 tracking to any project. Detects framework, adds tracking code, sets up events, and configures privacy settings.
agent-team-orchestration
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
agent-bom-enforce
Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".