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 machinarii/awesome-mental-models --skill awesome-mental-modelsgit clone --depth 1 https://github.com/machinarii/awesome-mental-modelsWrote 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/machinarii/awesome-mental-models/awesome-mental-models)<a href="https://agentmods.dev/skills/machinarii/awesome-mental-models/awesome-mental-models"><img src="https://agentmods.dev/badge/skills/machinarii/awesome-mental-models/awesome-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/machinarii/awesome-mental-models/awesome-mental-models"><img src="https://agentmods.dev/badge/skills/machinarii/awesome-mental-models/awesome-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 | $0.00127 | $0.01711 |
| Opus 5 | $0.00063 | $0.00856 |
| Sonnet 5 | $0.00025 | $0.00342 |
| Haiku 4.5 | $0.00013 | $0.00171 |
Grade B, and why
awesome-mental-models scanned grade B with 1 finding 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 11d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Never lecture from the file. Convert every step into a question about *their* problem. How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Awesome Mental Models
Pick the right mental model for the user's situation, then guide them through it as a working session — not a lecture.
The model files live at {{REPO_ROOT}}/mental-models/<slug>.md. The category index is at {{REPO_ROOT}}/mental-models.md. Each file has Overview, How to Use It, Example, Takeaway, Source. Use How to Use It as the spine of facilitation.
Order of operations: run Phase 0 FIRST — before consulting When-to-Use, When-NOT-to-Use, or any selection table. Even if the user's words match trigger phrases, Phase 0 runs first.
Phase 0 — Stakes Check (silent, gating)
Before doing anything else, silently answer:
- (a) Is this reversible within a week with no lasting cost?
- (b) Is the cost of being wrong less than an afternoon of work?
- (c) Is the user not asking for a framework — they want a quick take?
If (a) AND (b) are both YES, OR (c) is YES → bypass the protocol. Do NOT load a model.
Reply directly in 2–3 sentences answering the underlying question. Mention the framework option only if asked; do not narrate the bypass — just answer.
Only proceed to Phase 1 if a model would actually earn its keep.
When to Use
- User describes a real situation needing structured judgment
- Words like: decide, plan, prioritize, evaluate, fix, understand, communicate, learn, negotiate
- User explicitly asks for a model or framework
- User seems stuck, rationalizing, or asking "am I thinking about this right?"
When NOT to Use
- Pure factual questions ("what's X?")
- User has already named a model and wants the file content — just open
mental-models/<slug>.md - Cheap, reversible, low-stakes choice — running a model is overkill
The 5-Phase Protocol
- Frame — Restate the situation explicitly capturing all four:
- Goal (what is the user trying to do?)
- Stakes & reversibility (1-way door or 2-way door? Cost of being wrong?)
- Deadline (when must this be decided/done?)
- Decider / who's involved (solo, team, stakeholders, adversary?)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 124 lines · 127 tokens per session scan B bff31ef43834
awesome-mental-models is a skill published in the GitHub repository machinarii/awesome-mental-models (4 stars, last pushed 4mo ago), licensed MIT. It adds 127 tokens to every session and 1,711 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
master
Turn reference docs into active mastery through retrieval practice, case binding, and scenario simulation. Combines Skycak (learning science) and Chin (expertise acceleration) frameworks. Use when you want to deeply learn material, not just read it.
upskilling-coach
Expert coach for learning, mastering, and upskilling in any domain. Use when the user wants to learn, master, improve, upskill, get better at, or get coached on any topic. Helps build consistent practice habits, identify prerequisites, design efficient learning loops, avoid common pitfalls, maintain discipline, and…
book-recommender
A Chinese-language book recommendation and analysis skill that evaluates what books are about, whether they are worth reading, and how to read them.
history-autopsy
A structured overview of a major historical event or long-term historical process, covering its causes, development, results, and effects. It also connects the past to current events and adds memorable points for conversation.
learn-topic
A five-step lesson format for teaching a new subject to an experienced reader who is unfamiliar with that subject. It moves from an opening example through demonstration, explanation, guided practice, and independent practice with a self-check.
wisdom-decoder
A guided explanation skill for ideas from Buddhism, philosophy, and psychology. It presents a chosen topic in everyday language and connects it to practical actions, sources, and perspectives from other fields.