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-evolution-arms-racegit 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-evolution-arms-race)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-evolution-arms-race"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-evolution-arms-race/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-evolution-arms-race"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-evolution-arms-race.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 | $0.00093 | $0.02420 |
| Opus 5 | $0.00046 | $0.01210 |
| Sonnet 5 | $0.00019 | $0.00484 |
| Haiku 4.5 | $0.00009 | $0.00242 |
Grade A, and why
s4h-evolution-arms-race 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolution: Arms Race
Richard Dawkins and John Krebs described the evolutionary arms race in their 1979 paper "Arms Races Between and Within Species": predator and prey, host and parasite, competitor and competitor coevolve in a cycle of adaptation and counter-adaptation that neither party controls and from which neither may benefit in relative terms. The cheetah gets faster, the gazelle gets faster; the bacterium evolves resistance, the immune system evolves a new response; the advertising budget escalates, the competitor matches it. At the end of multiple rounds, relative positions may be unchanged. Both parties have invested heavily in capabilities that cancel each other out. This is the coevolutionary treadmill.
The arms race dynamic is distinct from straightforward competition. In ordinary competition, parties compete for the same resource and selection determines a winner. In an arms race, each party is the primary selective pressure on the other. The cheetah's speed is not limited by terrain or prey abundance — it is limited by the gazelle's speed. The structure creates escalation: any advantage one party gains becomes a selection pressure on the other, which responds, which becomes a selection pressure in return. The result is a feedback loop with no natural stopping point.
Van Valen's Red Queen hypothesis captures the relentless quality: organisms must keep evolving just to maintain their relative fitness against coevolving adversaries. "It takes all the running you can do to keep in the same place." This is why arms race analysis must ask not just "who is winning?" but "who benefits from the escalation continuing, and is there an exit?"
Your Process
Step 1: Identify the Coevolving Parties Name the entities involved. An arms race requires that each party's adaptations constitute the primary selection pressure on the other — their changes are what the other party is primarily responding to, not changes in the broader environment. Confirm this is true for the situation at hand: is each party primarily adapting to the other, or are both primarily adapting to a shared external pressure?
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 · 147 lines · 93 tokens per session scan A 4b88fa1c473a
s4h-evolution-arms-race is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 2,420 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.