What is poker_solver AGENTS.md?

Repository instructions for a Texas hold’em poker solver, covering its layout, commands, tests, and coding conventions. Texas hold’em is a card game, and a river subgame solver studies decisions after all but the final betting decisions.

Use it when modifying the solver, running tests or benchmarks, adding experiments, or deciding where new Python, C++, documentation, configuration, and generated results belong.

It gives coding agents the project rules and the expected way to build, test, and organize changes. It also explains that the Python version is the reference for checking the faster C++ version.

How noambrown/poker_solver configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to noambrown/poker_solver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/noambrown/poker_solver/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/noambrown/poker_solver

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/noambrown/poker_solver/agents-md/github.svg)](https://agentmods.dev/instructions/noambrown/poker_solver/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/noambrown/poker_solver/agents-md"><img src="https://agentmods.dev/badge/instructions/noambrown/poker_solver/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/noambrown/poker_solver/agents-md"><img src="https://agentmods.dev/badge/instructions/noambrown/poker_solver/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 646 This file is loaded in full into every session.

When invoked 646 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00646	$0.00646
Opus 5.5	$0.00258	$0.00258
Sonnet 5.5	$0.00129	$0.00129
Haiku 4.5	$0.00065	$0.00065

Measured 2mo ago against content hash b25147eca261, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

poker_solver AGENTS.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 2mo 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.

AGENTS.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Overview

This repo builds a no-limit Texas hold'em river subgame solver, starting with Kuhn and Leduc poker. Core algorithms include CFR, CFR+, external-sampling MCCFR, Fictitious Play (simul/alt), and FLOP. The Python implementation is the reference; the optimized C++ implementation lives in cpp/. Optimize only after matching Python results.

Project Structure & Module Organization

python/ reference implementation with python/src/algorithms/, python/src/games/, python/src/cli/, and python/tests/.
cpp/ optimized river solver (performance-focused).
docs/ design notes and algorithm references (add if needed).
configs/ run configs (YAML/JSON) for reproducible experiments (add if needed).
scripts/ or experiments/ reproducible runs and benchmarks (add if needed).
artifacts/ generated results; keep large outputs out of git (add if needed).

Build, Test, and Development Commands

Standardize developer commands in a Makefile (add if missing) and keep targets stable:

make setup - install dependencies and tooling.
make test - run the full test suite (all languages present).
make lint - static checks.
make fmt - formatting.
make run LANG=python GAME=kuhn ALGO=cfr - local run for a given game/algorithm. Until a Makefile exists, use direct commands like python -m pytest python/tests.

Coding Style & Naming Conventions

Indentation: 4 spaces, no tabs; keep files ASCII.
Names: snake_case for functions/modules, PascalCase for types, UPPER_SNAKE for constants.
Prefer pure functions and immutable data where practical; centralize RNG and logging.
Tooling: Python uses ruff (format/lint) and mypy (types); Rust uses rustfmt and clippy; C++ uses clang-format and clang-tidy once configured.

Testing Guidelines

Framework: pytest for Python unit and convergence tests.
Naming: python/tests/test_*.py; use deterministic seeds.
Add regression tests for exploitability thresholds on Kuhn/Leduc; ports must match these results.
Coverage: keep algorithm modules at >=90%; justify any exclusions.

Read the full file on GitHub · 44 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.

2mo ago First seen · 44 lines · 646 tokens per session scan A b25147eca261

Subscribe to this mod's changes

poker_solver AGENTS.md is an instructions file published in the GitHub repository noambrown/poker_solver (171 stars, last pushed 10mo ago), licensed MIT. It adds 646 tokens to every session, about $0.0026 per session on Opus 5.5. 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 2026-08-30.

poker_solver AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
poker_solver AGENTS.mdnoambrown/poker_solver	Instructions file	171	10mo ago	MIT	A	646	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

poker_solver: Instructions file for Codex