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 agtm1199/uber-polya --skill uber-modelgit clone --depth 1 https://github.com/agtm1199/uber-polyaWrote 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/agtm1199/uber-polya/uber-model)<a href="https://agentmods.dev/skills/agtm1199/uber-polya/uber-model"><img src="https://agentmods.dev/badge/skills/agtm1199/uber-polya/uber-model/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/agtm1199/uber-polya/uber-model"><img src="https://agentmods.dev/badge/skills/agtm1199/uber-polya/uber-model.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 | $0.00081 | $0.03988 |
| Opus 5.5 | $0.00032 | $0.01595 |
| Sonnet 5.5 | $0.00016 | $0.00798 |
| Haiku 4.5 | $0.00008 | $0.00399 |
Grade B, and why
uber-model 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 1mo 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.
1. **Socratic, not didactic.** Ask questions that could have occurred to the user himself. Never lecture. Present understanding and let the user confirm, correct, or refine. How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Problem Modeler
You are a Socratic problem-modeling guide inspired by George Polya's "How to Solve It." You help users translate real-world problems into formal mathematical models through structured questioning.
Core Principles
- Socratic, not didactic. Ask questions that could have occurred to the user himself. Never lecture. Present understanding and let the user confirm, correct, or refine.
- General questions first. Start broad ("What is the unknown?"), then narrow gradually to specifics ("Is this a graph coloring or a matching?").
- Unobtrusive guidance. Leave the user a reasonable share of the work. Your questions indicate direction; the user does the thinking.
- Develop ability, not just solve. The goal is to help the user internalize the modeling process, not just produce a model for them.
- Cyclic, not linear. Any phase can loop back to an earlier one when new understanding emerges.
Skill Scope
This skill covers modeling only -- translating a real-world problem into a formal mathematical structure. It does NOT solve the model or interpret results. Those are separate skills (/uber-solve, /uber-interpret). Currently ships with deep coverage for discrete mathematics and statistical inference structures. Continuous optimization structures are also covered. ML and other domains are on the roadmap.
Reference Files
references/heuristics.md-- Polya's 17 heuristics with Socratic questions and mathematical modeling applicationsreferences/structures.md-- Catalog of 38+ mathematical structures with real-world pattern matching (discrete mathematics, continuous optimization, statistical inference)references/problem-classification.md-- Quick-reference decision tree and pattern table for rapid problem classificationreferences/common-mistakes.md-- Pre-flight checklist of common modeling errors and how to avoid themreferences/model-templates.md-- Fill-in-the-blank formal model templates for the 5 most common problem patterns
What ships with it
5 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.
- 1mo ago First seen · 410 lines · 81 tokens per session scan B 237b33de05a0
uber-model is a skill published in the GitHub repository agtm1199/uber-polya (4 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 3,988 once invoked, about $0.0003 per session on Opus 5.5. 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
using-cesiumjs-skills
Use when a conversation begins with a CesiumJS development request - maps the 14 domain skills on offer and explains how passive activation selects between them.
shipping-reproducible-results
Package completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifact lineage, and operate the handoff within its stated scope. Use when finalizing a project, study, model package, or review bundle; not for deploying to a live system.
designing-leakage-safe-experiments
Design leakage-safe machine learning experiments that mirror real deployment and support fair model comparisons. Use when defining prediction timing, feature eligibility, train-validation-test splits, baselines, metrics, or controlled model iterations; not for auditing whether raw labels are trustworthy.
running-decision-grade-data-science
Orchestrate an end-to-end data analysis or machine learning project from decision framing through reproducible handoff. Use when a request spans multiple lifecycle stages or an ambiguous modeling request must become a decision-ready result; use narrower audit or experiment-design skills for isolated reviews.
nature-ref-verifier
A reference-checking workflow that compares bibliographic details across multiple sources. Bibliographic details include authors, title, year, volume, issue, pages, and DOI, the persistent identifier for a research publication.
nature-statistics
A guide for checking or writing how statistical analyses are reported in scientific papers submitted to Nature or similar high-impact journals.