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-information-entropygit 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-information-entropy)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-information-entropy"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-information-entropy/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-information-entropy"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-information-entropy.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 | $0.00074 | $0.02105 |
| Opus 5 | $0.00037 | $0.01052 |
| Sonnet 5 | $0.00015 | $0.00421 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
s4h-information-entropy 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information: Entropy
In 1948, Claude Shannon defined information in terms of surprise. The information content of a message is the degree to which it reduces your uncertainty. A message you could have predicted perfectly carries zero information — it tells you nothing you didn't already know. A completely unexpected message carries maximum information. Shannon called this quantity entropy, borrowing the term from thermodynamics: like physical entropy, it measures disorder and unpredictability.
Shannon entropy is defined as H = −∑ p(x) log₂ p(x) across all possible outcomes. The maximum entropy of a source is achieved when all outcomes are equally likely — pure unpredictability. Minimum entropy is achieved when one outcome is certain — pure predictability. Applied practically: a quarterly report that always says roughly the same thing carries low entropy. A dataset where any measurement could be anything carries high entropy. Neither extreme is ideal — maximum entropy is overwhelming, minimum entropy is uninformative.
Norbert Wiener extended this framework through cybernetics to argue that information is what distinguishes organisation from chaos in any self-regulating system. A thermostat carries information about temperature; the information is what allows the system to maintain order. Wiener's key insight: the entropic arrow runs toward decay unless information is actively used to correct it. Systems without good information channels become entropic — they drift.
Andrei Kolmogorov gave entropy a computational interpretation: the algorithmic complexity of a string is the length of the shortest program that can generate it. A truly random sequence cannot be compressed — it has maximum Kolmogorov complexity. A highly ordered sequence can be compressed to a short description — it has low complexity. The two frameworks — Shannon's probabilistic entropy and Kolmogorov's algorithmic complexity — converge: low-entropy sources are compressible; high-entropy sources are not.
The practical application is calibrating attention and weight. When a source has low entropy (high predictability), each new message from it should update you very little. When a source has high entropy (high surprise rate), each new message carries real information and deserves genuine engagement. Most people give equal attention to all messages regardless of their information content — this is the calibration error this skill corrects.
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 · 137 lines · 74 tokens per session scan A 795654a45785
s4h-information-entropy is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,105 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
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.