comparative-advantage

comparative-advantage is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 106 tokens per session (1,721 once invoked), scanned A, original, MIT.

An economics framework for deciding who should do which task by comparing relative strengths and trade-offs, rather than asking who is best overall. It explains why specialising can benefit a team even when one person is better at many tasks.

In plain words
What is it for?
Use it for team responsibilities, founder time, build-versus-buy choices, outsourcing, acquisitions, supply chains, and personal career specialisation.
Why use it?
Doing everything yourself or keeping work in-house can hide the time and opportunities lost elsewhere. This helps compare the full cost of doing, delegating, outsourcing, or buying work.

Skill for Claude CodeCodex

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

Good fit Use it for team responsibilities, founder time, build-versus-buy choices, outsourcing, acquisitions, supply chains, and personal career specialisation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/comparative-advantage
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 deciqAI/knowledge-skills --skill comparative-advantage
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-skills

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 comparative-advantage

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/comparative-advantage.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/comparative-advantage)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/comparative-advantage"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/comparative-advantage.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,721 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00106 $0.01721
Opus 5 $0.00053 $0.00860
Sonnet 5 $0.00021 $0.00344
Haiku 4.5 $0.00011 $0.00172

Measured 8d ago against content hash 2666452f3dcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

comparative-advantage 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 8d 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.

comparative-advantage/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Comparative Advantage

Overview

Mutually beneficial specialization depends on relative productivity, not absolute. Even if you are better than everyone else at every task, you gain by focusing on tasks where your opportunity-cost ratio is lowest and delegating the rest. The right question is not "am I better at X than them?" but "am I better at X relative to Y compared to how they are?"

Proved by David Ricardo (1817); called "the only proposition in economics that is both true and non-obvious" by Paul Samuelson (1969).

Composes with opportunity-cost, pareto-principle, circle-of-competence, theory-of-constraints.

When to Use

  • Founder time allocation across activities; team division of labor
  • Build vs. buy / in-house vs. outsource decisions
  • M&A decisions; international operations / supply chain design (e.g. AI-chip re-shoring, chip export controls, semiconductor vertical integration)
  • Personal career or skill specialization decisions

Not when: situation is genuinely single-task (no B to trade off); transaction costs swamp any gains; alternative producer's capacity is fully constrained.

Coaching Novices (Adaptive Front Door)

  • Engine mode: user has a concrete allocation decision → run The Process directly.
  • Coach mode: user is unfamiliar or has no concrete case → guide step by step.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

  1. One-line: the right test is not "am I better than them at this?" but "am I better at this relative to what else I could be doing?"
  2. Check fit: if single-task or transaction costs very high, analysis adds limited value.
  3. Elicit the case: what are you considering doing? What else could you do with the time? Who else could do it?

[WAIT — do not advance until user responds]

  1. One question at a time: what's your opportunity cost of the focal task? What's the alternative producer's OC? Where do ratios diverge? Are transaction costs material?

[WAIT — do not advance until user responds]

  1. Close: specialization recommendation + transaction-cost caveat + monitoring plan.

[WAIT — do not advance until user responds]

Read the full file on GitHub · 119 lines

Files

What ships with it

4 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.

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. 8d ago First seen · 119 lines · 106 tokens per session scan A 2666452f3dcf

Subscribe to this mod's changes

comparative-advantage is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 6d ago), licensed MIT. It adds 106 tokens to every session and 1,721 once invoked, about $0.0005 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.

Related

Other skills, from other repositories