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-variation-selectiongit 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-variation-selection)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-evolution-variation-selection"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-evolution-variation-selection/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-variation-selection"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-evolution-variation-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 56 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00075 | $0.02022 |
| Opus 5 | $0.00037 | $0.01011 |
| Sonnet 5 | $0.00015 | $0.00404 |
| Haiku 4.5 | $0.00007 | $0.00202 |
Grade A, and why
s4h-evolution-variation-selection 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evolution: Variation-Selection
Darwin's central insight was not about progress — it was about fit. Populations change not because individuals strive toward an ideal but because variants that happen to be better suited to current conditions leave more descendants. The population shifts toward fitness not through intention but through differential survival and reproduction. Evolution is a filter, not a designer.
This tool applies the variation-selection-retention triad to any evolving system: biological populations, business strategy portfolios, cultural practices, product features, organisational structures, or ideas spreading through a community. Whenever there is a population of variants, a selection environment that differentially rewards some over others, and a mechanism by which successful variants are retained or replicated — evolution is happening. The analysis asks: what is varying, what is the selection pressure, what is being retained, and what does the population look like after several rounds?
Richard Dawkins extended Darwin's logic beyond genes to any replicating entity with heritable variation — memes, strategies, cultural norms. The triad is substrate-independent: wherever variation + selection + retention operate, populations evolve. The question is always which variants win in this environment, not which are best in the abstract.
Your Process
Step 1: Define the Population and the Entity Identify what is being evolved. What are the entities in this population — the variants being compared? Be precise: not "companies" but "pricing strategies in use by companies in this market." Define the time horizon over which evolution is being observed: one product cycle, ten years, a generation.
Framing check: Confirm the population and time horizon before continuing. State what you've identified — the specific entities being varied, the time scale, and the outcome space — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing — what the population is, what varies, and over what time horizon]. 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 · 136 lines · 75 tokens per session scan A 54c1d0e53ff5
s4h-evolution-variation-selection is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,022 once invoked, about $0.0004 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
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.
fulcra-lab-results
Parse a lab-report PDF (LabCorp, Quest, hospital labs — any provider) into one canonical Fulcra data track per marker (LDL-C, HbA1c, TSH, ferritin, …). You read the PDF; the fulcra-labs engine normalizes units, validates, and ingests. Verify-before-ingest: nothing is written without passing validation or explicit…
figure-craft
Use when making a FIGURE / CHART / PLOT for a paper, deck, or presentation — in ANY language (R/ggplot2, Python/matplotlib, Julia/Makie). Governs the visual style: 16.5pt text throughout (axes, legend, title), no y-label (the title carries the y-axis meaning; paper figures get no headline title), concise axis labels…
executing-analysis-plans
Use once an analysis brief or pre-analysis plan is APPROVED and it's time to actually run the analysis — build the dataset, estimate the primary specification, run the robustness suite, placebo tests, and alternative designs, then assemble the results. Drives execution through the plan step by step, validating each…
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 Task subagent per panel (each loads figure-style) → tile + stamp letters →…
pre-analysis-plan
Use BEFORE running a confirmatory analysis, an experiment readout, an A/B test, a policy evaluation, or any study whose credibility depends on not having fished for the result — especially causal/econometric work. Locks the hypotheses, estimand, primary specification, sample and exclusions, and the robustness suite…