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 instructions/agtm1199/uber-polya/copilot-instructionsgit 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/instructions/agtm1199/uber-polya/copilot-instructions)<a href="https://agentmods.dev/instructions/agtm1199/uber-polya/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/agtm1199/uber-polya/copilot-instructions.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 | $0.00437 | $0.00437 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
uber-polya copilot-instructions.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 3d 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
uber-polya
This project is a mathematical problem-solving engine implementing George Polya's "How to Solve It" methodology. It solves real-world problems through a three-phase pipeline: Model (formalize the problem), Solve (implement and verify), Interpret (translate to actionable insight).
When a User Presents a Problem
Follow the full protocol in docs/methodology.md and AGENTS.md.
Pipeline Summary
- Phase A -- Model: Classify the problem (Find vs. Prove). Consult
skills/uber-model/references/for pattern matching against 91 mathematical structures. Build a formal model with a real-world-to-math mapping table. - Phase B -- Solve: Select an algorithm from the 305 cataloged in
skills/uber-solve/references/. Implement a Python solver withInstance/Solutiondataclasses,solve(), andverify()functions. Verify independently. - Phase C -- Interpret: Consult
skills/uber-interpret/references/. Reverse the mapping. Run sensitivity analysis. Generate visualizations. Provide actionable recommendations.
Key Convention
Ask the user to confirm at each phase gate before proceeding to the next phase.
Python Code
Solvers use Python 3.10+, dataclass(frozen=True) for Instance, separate verify() function, time.perf_counter() for timing, type hints on all signatures. See docs/methodology.md for the full template.
Output Format
The pipeline supports three output formats (ask the user before starting):
- Python (default): solver script + console output + JSON
- LaTeX/PDF: professional mathematical report (
.tex+.pdf), no code shown - Both: full Python output AND compiled PDF report
PDF generation uses fpdf2 + matplotlib (no system LaTeX needed). See utils/latex_renderer.py and templates/latex/.
Worked Examples
See examples/ for 36 fully worked problems with runnable solver scripts.
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.
- 3d ago First seen · 35 lines · 437 tokens per session scan A ea6116d1a99d
uber-polya copilot-instructions.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 437 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
PPT-Design-Skill CLAUDE.md
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.
kortex AGENTS.md
Instructions for Heapy/kortex, covering kortex, layout, specs, agents and releasing.
skills AGENTS.md
Instructions for bitwise-media-group/skills, covering bitwise skills — repository conventions, layout, dual manifests (claude + codex), skill frontmatter policy and progressive disclosure.
arkgum-agent-skills AGENTS.md
Instructions for arkgum/arkgum-agent-skills, covering repository instructions, skill contract, public-safety contract and repository maintenance.
agent-skills CLAUDE.md
Claude Code instructions for motherduckdb/agent-skills, covering motherduck skills -- claude code context, what motherduck is, default routing, install notes and non-negotiable rules.
agent-skills GEMINI.md
Gemini CLI instructions for motherduckdb/agent-skills, covering motherduck skills for gemini cli, default routing, skill catalog, utility and workflow.