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-fitness-landscapegit 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-fitness-landscape)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-evolution-fitness-landscape"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-evolution-fitness-landscape/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-fitness-landscape"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-evolution-fitness-landscape.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 | $0.00088 | $0.02305 |
| Opus 5.5 | $0.00035 | $0.00922 |
| Sonnet 5.5 | $0.00018 | $0.00461 |
| Haiku 4.5 | $0.00009 | $0.00231 |
Grade A, and why
s4h-evolution-fitness-landscape 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 1mo 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: Fitness Landscape
Sewall Wright introduced the fitness landscape metaphor in 1932: imagine every possible combination of traits mapped onto a surface, with elevation representing fitness. Populations move across this surface by natural selection — uphill, always, toward higher fitness. The metaphor contains a profound trap: gradient-following reliably finds local peaks but may never reach the global optimum if that optimum is separated from the current position by a valley — a region of lower fitness that must be crossed to reach higher ground.
Stuart Kauffman formalised the implications. In a rugged landscape (many local peaks of varying heights), adaptive evolution produces a rich variety of stable-but-suboptimal solutions. Path dependence is total: where you end up depends entirely on where you started, because the trajectory of selection is irreversible and local. In an ultra-smooth landscape (one peak), selection reliably finds the global optimum. In a chaotic landscape (fitness changes with every step), selection fails entirely — there is no stable higher ground to climb toward.
This tool maps the fitness landscape of a problem, strategy space, or technology domain. It identifies where the current entity sits, which kind of landscape this is, what the local peaks look like, what valleys must be crossed to reach higher ground, and whether valley-crossing is currently viable. The practical question is almost always: are we trapped on a local peak, and if so, what does it cost to get off it?
Your Process
Step 1: Define the Landscape Specify the axes and the fitness measure. Every landscape has:
- Axes (trait dimensions): the variables that can be changed. In evolution, these are genetic traits. In strategy, they might be product features, business model parameters, technology architecture, pricing approach, or organisational structure. Identify the 2–4 most important axes — those where variation most strongly affects fitness.
- Fitness measure: what counts as success in this environment? Be specific — not "performance" but "customer retention at a given price point" or "survival rate in a drought year." The fitness measure is always context-dependent and time-indexed.
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.
- 1mo ago First seen · 147 lines · 88 tokens per session scan A eb2419de9daf
s4h-evolution-fitness-landscape is a skill published in the GitHub repository human-avatar/skills-for-humanity (236 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 2,305 once invoked, about $0.0004 per session on Opus 5.5. 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
thinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure via deriveoutlinetask(png). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → fan-out one subagent per panel (each loads figure-style) → tile + stamp letters → adversarial…
paper-narrative
Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. derivepaperbrieftask(abstract, captions) builds the prompt whose JSON is pitch/vision/per-figure-claims; a handling-editor reviewer on the full deck returns hookverdict (would…
creating-figures
Creates publication-quality scientific figures for academic papers. Backend is chosen by host paper extension — .tex papers get TikZ figures, .typ papers get CeTZ figures; the two are never mixed. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses.…
literature-landscape
Generate figures that visualize patterns in an academic literature: publication trends, citation landmarks, journal distributions, thematic evolution, method timelines, and coverage gap maps. Uses Corbis search data and Python/matplotlib.
paper-writing
A writing workflow for producing a social-science research paper from an approved research design, cited prior studies, and analysis results.