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-cognition-mental-modelsgit 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-cognition-mental-models)<a href="https://agentmods.dev/skills/human-avatar/skills-for-humanity/s4h-cognition-mental-models"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-cognition-mental-models/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-cognition-mental-models"><img src="https://agentmods.dev/badge/skills/human-avatar/skills-for-humanity/s4h-cognition-mental-models.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 | $0.00087 | $0.01723 |
| Opus 5 | $0.00044 | $0.00861 |
| Sonnet 5 | $0.00017 | $0.00345 |
| Haiku 4.5 | $0.00009 | $0.00172 |
Grade A, and why
s4h-cognition-mental-models 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 13d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognition: Mental Models
Every perception, judgment, and decision runs through a mental model. Philip Johnson-Laird's model theory, developed through decades of research at Princeton, demonstrated that human reasoning does not operate on formal logical rules — it operates on internal simulations of situations. We construct small-scale models of reality, reason by running those models mentally, and check conclusions against them. The problem is not that we use mental models — it's that the models become invisible.
When a mental model is invisible, it cannot be examined. Its assumptions are treated as facts. Its gaps become blind spots. Its distortions shape what evidence we notice and what options we can imagine, all without our awareness. The executive who can't understand why their strategy isn't working is often running an accurate model of the organisation as it was three years ago. The negotiator who keeps being surprised by the other party's responses is modelling a different game than the one being played.
This skill makes the implicit explicit. It identifies which models are active in a situation, extracts their assumptions, tests those assumptions against available evidence, and identifies where the model is incomplete, outdated, or simply wrong. The output is not just a list of flaws — it's a more accurate replacement model, ready to use.
Your Process
Step 1: Identify the Model in Use Ask: what are the implicit beliefs about how this domain works that are driving the current perception or decision? A mental model has three components:
- Entities: the actors, objects, or forces in the model
- Relationships: how those entities interact and influence each other
- Dynamics: how the model behaves over time — what causes what, what follows from what
Name the current model in explicit terms. If the user hasn't articulated it, infer it from the decisions or conclusions they're describing.
Framing check: Confirm the specific model and situation before continuing. State what you've identified — the domain being modelled and the decision or belief the model is shaping — in one sentence, then use AskUserQuestion:
- Question: "I'm reading this as: [your one-sentence framing of the domain, the current model, and the decision it's shaping]. 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.
- 13d ago First seen · 123 lines · 87 tokens per session scan A d5a4f4c92011
s4h-cognition-mental-models is a skill published in the GitHub repository human-avatar/skills-for-humanity (223 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,723 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 2026-08-30.
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.