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 human-avatar/skills-for-humanity --skill s4h-game-theory-iteratedgit clone --depth 1 https://github.com/human-avatar/skills-for-humanityWrote 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/human-avatar/skills-for-humanity/s4h-game-theory-iterated)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-game-theory-iterated"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-game-theory-iterated/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/human-avatar/skills-for-humanity/s4h-game-theory-iterated"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-game-theory-iterated.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.02055 |
| Opus 5 | $0.00050 | $0.01027 |
| Sonnet 5 | $0.00020 | $0.00411 |
| Haiku 4.5 | $0.00010 | $0.00205 |
Grade A, and why
s4h-game-theory-iterated 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Theory: Iterated Games
Robert Axelrod's 1984 computer tournament is one of the most important results in social science. He invited game theorists to submit strategies for an iterated prisoners' dilemma — a repeated game where the same two players interact over and over. The simplest strategy submitted, Tit for Tat (cooperate on the first move, then do exactly what your opponent did on the previous move), won both rounds of the tournament, beating every more complex strategy.
Why Tit for Tat wins: it is nice (starts by cooperating, never the first to defect), retaliatory (immediately punishes defection — there is no free lunch), forgiving (returns to cooperation as soon as the opponent does — does not hold grudges), and clear (the strategy is transparent and easy for the opponent to understand). Opponents who try to exploit it get punished; opponents who cooperate get rewarded. It is the most robust known strategy for sustained cooperation without trust.
The folk theorem establishes the theoretical foundation: in infinitely (or indefinitely) repeated games with sufficiently patient players, almost any outcome — including full cooperation — can be sustained as a Nash equilibrium, because the threat of future punishment makes defection unprofitable. The key variable is the discount factor (how much players value future payoffs relative to present ones), and whether punishment is credible and observable.
Your Process
Step 1: Stage game Describe the single-period interaction — what are the two players' choices in any given round, and what are the payoffs? Map the four key payoffs: mutual cooperation (CC), mutual defection (DD), exploitation (one cooperates, one defects), and being exploited. This identifies whether repetition can help: if the stage game already has cooperation as a Nash equilibrium, repetition changes little. If cooperation is not a Nash equilibrium of the stage game, repetition may enable it.
Framing check: Confirm the repeated interaction before continuing. State what you've identified — the two parties involved, the recurring choice or tension, and the relationship context — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the specific repeated interaction, the parties, and what cooperation/defection looks like in this context]. Is that right?"
- Header: "Framing"
- Options:
- Yes — proceed — framing is correct
- Adjust — one element is off; user will correct it before you continue
- Reframe — different situation than read; incorporate the correction before proceeding
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.
- 9d ago First seen · 130 lines · 100 tokens per session scan A 2e9fb0e4ed35
s4h-game-theory-iterated is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 2,055 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 2026-09-03.
Other skills, from other repositories
decision-making-under-pressure
Provides practical habits for making better decisions faster -- reframing problems before solving them, knowing when to stop deliberating, balancing intuition with analysis, resisting 'just this once' compromises, and breaking overthinking cycles. Use when facing a high-stakes choice with incomplete data, sensing that…
flow-state
Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…
stoic-right-action
Applies Stoic ethics of right action to entrepreneurial decision-making, covering the four cardinal virtues (courage, justice, temperance, wisdom), ethical leadership under pressure, and the discipline of choosing the harder right over the easier wrong. Use when facing ethical dilemmas in business, building a…
bakeoff
Turn one decision into a judged tournament of solutions, then pick the best. Given a problem, design choice, or a suggestion you want cross-verified, it generates diverse candidate solutions, auto-derives the evaluation dimensions for THAT problem (so you don't have to know what to score on), judges every candidate…
balanced-scorecard
Translate strategy into metrics across Financial, Customer, Internal Process, and Learning & Growth perspectives.
customer-journey-map
Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.