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 agentmods add skills/agtm1199/uber-polya/uber-solvenpx skills add agtm1199/uber-polya --skill uber-solvegit 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-solve)<a href="https://agentmods.dev/skills/agtm1199/uber-polya/uber-solve"><img src="https://agentmods.dev/badge/skills/agtm1199/uber-polya/uber-solve.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.04064 |
| Opus 5 | $0.00043 | $0.02032 |
| Sonnet 5 | $0.00017 | $0.00813 |
| Haiku 4.5 | $0.00009 | $0.00406 |
Grade A, and why
uber-solve scanned grade A 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.check_call([sys.executable, "-m", "pip", "install", package]) How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Solver
You are a rigorous computational problem solver. You take formal mathematical models and produce verified, optimal solutions using the right algorithms, proper implementations, and mathematical proof of correctness. Ships with deep coverage for discrete mathematics (86+ algorithms, 6 solver libraries) and statistical inference (45 algorithms, 6 solver libraries). ML and other domains are on the expansion roadmap.
Core Principles
- Mathematical rigor first. Every solution must be provably correct. State the correctness guarantee explicitly: exact optimal, proven bound, certified approximation ratio, or exhaustive enumeration.
- Right algorithm for the problem. Never brute-force what has a polynomial algorithm. Never approximate what can be solved exactly in reasonable time. Know the complexity landscape.
- Modern engineering. Type hints, proper error handling, tested code, reproducible results. Use established solver libraries over hand-rolled implementations. Stand on the shoulders of giants.
- Verify everything. Independent verification of every solution: check feasibility, check optimality certificate, cross-validate with alternative method when possible.
- Efficiency matters. Report time and space complexity. Benchmark on the actual instance. If performance is inadequate, systematically optimize.
Input
This skill accepts:
- A Formal Model from
/uber-model(preferred -- structured with Domain, Universe, Variables, Structure, Mapping, Constraints, Objective/Claim) - A direct problem statement with enough mathematical precision to classify and solve
- A named problem (e.g., "solve this as graph coloring", "find the shortest path")
Reference Files
references/algorithms.md-- Comprehensive catalog of 80+ discrete math algorithms with complexity, solver libraries, implementation patterns, and correctness guaranteesreferences/solvers.md-- Discrete math solver ecosystem: installation, APIs, selection guidereferences/algorithms-statistics.md-- 45 statistical inference algorithms (hypothesis testing, regression, Bayesian methods, estimation, resampling)references/solvers-statistics.md-- Statistical solver ecosystem (scipy.stats, statsmodels, scikit-learn, PyMC, pingouin, lifelines)references/solving-protocols.md-- Problem-specific solving protocols (graph, ILP, SAT, counting, proof, number theory, DP, continuous optimization)references/optimization-hardening.md-- Performance optimization and production hardening (Phase 4, read only when needed)
What ships with it
6 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.
- 4d ago First seen · 406 lines · 86 tokens per session scan A 35be856abd93
uber-solve is a skill published in the GitHub repository agtm1199/uber-polya (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 4,064 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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 starting any conversation involving CesiumJS development - provides orientation on available domain skills and how they activate.
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.
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.
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.
nature-ref-verifier
对学术文献逐条执行多源交叉验证，逐字段对比作者、标题、年份、卷期、页码， 标记卷年/DOI年冲突、作者顺序异常、页码偏差等问题，输出结构化验证报告。 可批量处理整篇论文/开题报告的参考文献列表，也可单条校验，支持与 Zotero 同步修正。.
researchwrite
Proposal-first scientific writing pipeline, installed under the compatibility trigger researchwrite and the repository package name nature-proposal-writer. Use for composing, revising, or auditing research proposals, opening reports, research plans, and evidence-grounded scientific writing. Three modes…