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.
git 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/rules/agtm1199/uber-polya/solver-conventions)<a href="https://agentmods.dev/rules/agtm1199/uber-polya/solver-conventions"><img src="https://agentmods.dev/badge/rules/agtm1199/uber-polya/solver-conventions/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/rules/agtm1199/uber-polya/solver-conventions"><img src="https://agentmods.dev/badge/rules/agtm1199/uber-polya/solver-conventions.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 | $0.00000 | $0.00341 |
| Opus 5.5 | $0.00000 | $0.00136 |
| Sonnet 5.5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
solver-conventions 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 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.
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
Solver Conventions
Python 3.10+ solvers must follow these standards:
Required Structure
#!/usr/bin/env python3
"""[Problem name] solver. O([complexity]). [Correctness guarantee]."""
from __future__ import annotations
import time
from dataclasses import dataclass
@dataclass(frozen=True)
class Instance:
"""Immutable problem instance."""
...
@dataclass
class Solution:
"""Solution with metadata."""
value: ...
objective: float | None
is_optimal: bool
is_feasible: bool
algorithm: str
time_seconds: float
certificate: str | None
def solve(instance: Instance) -> Solution:
t0 = time.perf_counter()
# ... algorithm ...
elapsed = time.perf_counter() - t0
return Solution(...)
def verify(instance: Instance, solution) -> bool:
"""Independent verification. Must NOT share logic with solve()."""
...
Rules
- Type hints on all function signatures
from __future__ import annotationsat top@dataclass(frozen=True)for Instance,@dataclassfor Solutiontime.perf_counter()for timing (nottime.time())solve()andverify()must be separate with no shared logic- Deterministic output (seed RNG if randomized)
- Handle edge cases: n=0, n=1, disconnected, infeasible, unbounded
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 · 55 lines · 0 tokens per session scan A fd407391d2d9
solver-conventions is a cursor rule published in the GitHub repository agtm1199/uber-polya (4 stars, last pushed 7mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 341 tokens. 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 cursor rules, from other repositories
numpy
This guide provides definitive, actionable best practices for writing high-performance, maintainable, and correct NumPy code, emphasizing vectorization, explicit dtypes, and modern GPU acceleration.
scikit-image
This guide defines the definitive best practices for developing with scikit-image, ensuring maintainable, performant, and robust image processing code.
scipy
This guide provides opinionated, actionable best practices for writing robust, performant, and maintainable Python code using SciPy, aligning with modern scientific computing standards.
pyqt6-eeg-processing-cursorrules-prompt-file
Cursor rule "pyqt6-eeg-processing-cursorrules-prompt-file" from XD3an/awesome-ai-coding-all-in-one, covering ai system prompt for master python programmer, general instructions for implementation and example usage.
cursorrules
You are building an AI/ML project with Python. The project uses PyTorch for model training, handles data pipelines with proper validation, tracks experiments systematically, and follows production ML engineering practices. Code is type-hinted, tested, and reproducible.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.