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.
git clone --depth 1 https://github.com/Amey-Thakur/AI-SKILLSWrote 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/commands/amey-thakur/ai-skills/mental-models)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/mental-models"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/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/commands/amey-thakur/ai-skills/mental-models"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/mental-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.00379 |
| Opus 5 | $0.00010 | $0.00189 |
| Sonnet 5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
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 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Analyze this using relevant mental models: {problem}
Context: {context}
Pick the 3-5 mental models that genuinely illuminate THIS problem (not a generic list), and apply each concretely:
- For each model: name it, state it in a sentence, then apply it to my specific situation and say what it reveals: an insight, a risk, a reframe I would miss otherwise.
- Draw from the useful ones as they fit: inversion (what would guarantee failure?), opportunity cost, second-order effects, incentives (who is motivated to do what?), first principles, the map is not the territory, base rates, margin of safety, Occam's razor, sunk cost, leverage points, bottlenecks, and others that suit the problem.
- Where models disagree or pull in different directions, say so: the tension is often where the real insight is.
Finish with the synthesis: what the models together suggest, and the 1-2 that matter most here.
Rules: apply models to my actual situation, do not just define them (a definition helps nobody; the application is the value). Pick for relevance, not to show off breadth. Be honest where a model does not fit or would mislead. The goal is a clearer, less biased view of the problem, so surface what my own framing is hiding.
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 · 41 lines · 19 tokens per session scan A eb77497a1abb
mental-models is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 379 once invoked, about $0.0001 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 commands, from other repositories
present
Prepare a product presentation.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.