agentmods.dev

uber-polya CLAUDE.md

uber-polya CLAUDE.md is an instructions file for coding agents from agtm1199/uber-polya. It costs 1,598 tokens per session, scanned A, original, Apache-2.0.

A set of Claude Code instructions that applies George Pólya’s “How to Solve It” problem-solving method through separate skills for modelling problems, solving them, and explaining the results.

In plain words
What is it for?
Use it to organise complex problem-solving work, choose suitable algorithms or solvers, and produce reports with LaTeX templates, code examples, or visualisations.
Why use it?
It gives the agent a structured way to move from a real-world question to a mathematical model, a checked solution, and practical conclusions.

Instructions file

not rated 4 6mo ago A scan 1,598 tokens original Apache-2.0
View the source file agtm1199/uber-polya
Install

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.

agentmods
npx agentmods add instructions/agtm1199/uber-polya/claude-md
Clone the repo
git clone --depth 1 https://github.com/agtm1199/uber-polya

Wrote 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.

agentmods badge for uber-polya CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/agtm1199/uber-polya/claude-md.svg)](https://agentmods.dev/instructions/agtm1199/uber-polya/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/agtm1199/uber-polya/claude-md"><img src="https://agentmods.dev/badge/instructions/agtm1199/uber-polya/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,598 This file is loaded in full into every session.
When invoked 1,598 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01598 $0.01598
Opus 5 $0.00799 $0.00799
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 4d ago against content hash 063abd24334a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uber-polya CLAUDE.md 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 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.

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.

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

uber-polya

Universal problem-solving engine for Claude Code, implementing George Polya's "How to Solve It" methodology as modular skills.

Project Structure

skills/
  uber-polya/     -- Orchestrator: chains the full pipeline
  uber-model/     -- Phase A: real-world problem → formal mathematical model
    references/   -- heuristics, structures, problem-classification, common-mistakes, model-templates
  uber-solve/     -- Phase B: formal model → verified solution
    references/   -- algorithms, solvers, algorithms-statistics, solvers-statistics, solving-protocols, optimization-hardening
  uber-interpret/ -- Phase C: solution → actionable insight
    references/   -- interpretation-patterns, visualization
templates/
  latex/          -- Jinja2 LaTeX templates + polya.sty style for PDF reports
examples/         -- Worked examples with solver code and visualizations
docs/             -- Architecture, tutorials, contributing guide

How Skills Work

Each skill is a directory under skills/ containing a SKILL.md and a references/ folder. The SKILL.md is loaded when the user invokes /skill-name. Reference files are read on demand (not at invocation) to keep context overhead low.

Conventions

SKILL.md files

  • YAML frontmatter with name and description (description contains trigger phrases)
  • Structured phases with numbered steps
  • Phase gates use AskUserQuestion for user confirmation
  • Self-check lists after each gate
  • Reference files are read via explicit Read tool calls at the specified phase
  • Keep SKILL.md under 500 lines; move situational content to reference files

Reference files

  • Markdown format with consistent heading structure
  • Each entry should be self-contained (definition, when to use, example)
  • Use tables for quick-lookup content (algorithm selection, chart selection, pattern matching)
  • Cross-reference other files by relative path when relevant

Worked examples

  • Each example gets its own directory under examples/
  • Required files: README.md, solver script (Python), sample input/output
  • Solver scripts use dataclass for Instance and Solution, with separate solve() and verify() functions
  • Visualization scripts save to PNG (not committed to repo)

Read the full file on GitHub · 95 lines

Changes

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.

  1. 4d ago First seen · 95 lines · 1,598 tokens per session scan A 063abd24334a

Subscribe to this mod's changes

uber-polya CLAUDE.md is an instructions file published in the GitHub repository agtm1199/uber-polya (4 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,598 tokens to every session, about $0.0080 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 2026-08-31.

Learning and teachingPlanningai-agentclaude-codeclaude-code-skillscodexcodex-skillsconstraint-satisfaction
Related

Other instructions, from other repositories

edu-agent-skills AGENTS.md

Instructions for yugash007/edu-agent-skills, covering agents.md, project contract, teaching philosophy, repository-wide educational principles and skill conventions.

yugash007/edu-agent-skills · 569 tokens

PPT-Design-Skill CLAUDE.md

Claude Code instructions for sunchaokun/PPT-Design-Skill: Use the ppt-design-skill workflow for presentation design tasks. The published pptx-designer Python library creates the editable PPTX; this repository owns the design process, installation, rendering, and PNG review.

sunchaokun/PPT-Design-Skill · 139 tokens

kortex AGENTS.md

AGENTS.md instructions for Heapy/kortex, covering kortex, layout, specs, agents and releasing.

Heapy/kortex · 1,306 tokens

skills AGENTS.md

AGENTS.md instructions for bitwise-media-group/skills, covering bitwise skills — repository conventions, layout, dual manifests (claude + codex), skill frontmatter policy and progressive disclosure.

bitwise-media-group/skills · 1,495 tokens

arkgum-agent-skills AGENTS.md

Instructions for arkgum/arkgum-agent-skills, covering repository instructions, skill contract, public-safety contract and repository maintenance.

arkgum/arkgum-agent-skills · 284 tokens

agent-skills GEMINI.md

Gemini CLI instructions for motherduckdb/agent-skills, covering motherduck skills for gemini cli, default routing, skill catalog, utility and workflow.

motherduckdb/agent-skills · 883 tokens