agentmods.dev

baba-is-auto AGENTS.md

baba-is-auto AGENTS.md is an instructions file for Codex, OpenCode from utilForever/baba-is-auto. It costs 1,680 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on a C++17 Baba Is You simulator with reinforcement-learning examples, a graphical interface, an editor, and a Python interface.

In plain words
What is it for?
Understanding where simulator, Python, GUI, editor, map, and training files live, and checking mirrored implementations before making changes.
Why use it?
They explain the project’s split structure and warn agents to keep the core simulator and its Python binding in sync when changing behavior.

Instructions file for CodexOpenCode

not rated 191 changed today A scan 1,680 tokens original MIT
View the source file utilForever/baba-is-auto
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/utilforever/baba-is-auto/agents-md
Clone the repo
git clone --depth 1 https://github.com/utilForever/baba-is-auto

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.

agentmods badge for baba-is-auto AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/utilforever/baba-is-auto/agents-md.svg)](https://agentmods.dev/instructions/utilforever/baba-is-auto/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/utilforever/baba-is-auto/agents-md"><img src="https://agentmods.dev/badge/instructions/utilforever/baba-is-auto/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,680 This file is loaded in full into every session.
When invoked 1,680 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 $0.01680 $0.01680
Opus 5 $0.00840 $0.00840
Sonnet 5 $0.00336 $0.00336
Haiku 4.5 $0.00168 $0.00168

Measured today against content hash 2f97d89643cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

baba-is-auto 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 today.

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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI coding agents (Codex, Claude Code, etc.) working in this repository. Humans should start with README.md; this file restates the project rules in the operational order an agent needs them.

What this repository is

This is baba-is-auto, a C++17 Baba Is You simulator with reinforcement learning examples, a pygame GUI, an optional C++ ImGui level editor, and a Python API exposed through pybind11.

It is not just a single C++ library:

  • The core simulator is in Includes/baba-is-auto/ and Sources/baba-is-auto/.
  • The Python extension under Extensions/BabaPython/ mirrors parts of the core API and implementation.
  • Python GUI/RL examples consume the Python-facing behavior from Extensions/BabaGUI/ and Extensions/BabaRL/.
  • The optional C++ level editor lives in Extensions/BabaEditor/.
  • Test fixtures and sample levels live in Resources/Maps/.

Upstream lives at https://github.com/utilForever/baba-is-auto.git.

Golden rules (read before any change)

  1. Keep the C++ core and Python binding in sync. If you change game, map, rule, enum, object, or agent behavior in the core library, check whether the mirrored files under Extensions/BabaPython/ need the same update.
  2. Do not hand-edit generated aggregate headers casually. Includes/baba-is-auto.hpp is generated by Scripts/header_gen.py during the CMake build. Change headers or the generator instead of treating the generated file as the primary source.
  3. Use CMake targets as the source of truth. Before adding or moving C++ files, read the relevant CMakeLists.txt so the intended target will build on Ubuntu, macOS, and Windows.
  4. Preserve C++17 portability. Avoid compiler-specific assumptions unless they are guarded by CMake or clearly isolated.
  5. Do not add unpinned Python dependencies. requirements.txt is hash-pinned and CI installs it with --require-hashes.
  6. Run the relevant tests before considering behavior changes complete. Documentation-only changes usually do not need a build, but code or API changes should be verified with the commands below.

Read the full file on GitHub · 121 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. today Changed · +4 lines · +30 tokens per session 2f97d89643cd
  2. 4d ago First seen · 117 lines · 1,650 tokens per session scan A 98ee7965242e

Subscribe to this mod's changes

baba-is-auto AGENTS.md is an instructions file published in the GitHub repository utilForever/baba-is-auto (191 stars, last pushed 3d ago), licensed MIT. It adds 1,680 tokens to every session, about $0.0084 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 2026-08-30.

C and C++Planningbaba-is-youbabaisyoureinforcement-learningrlrl-environment
Related

Other instructions, from other repositories

RosettaStone AGENTS.md

AGENTS.md instructions for utilForever/RosettaStone, covering agents.md, what this repository is, golden rules (read before any change), common task flow and hearthstone model.

utilForever/RosettaStone · 3,108 tokens

AReaL AGENTS.md

AGENTS.md instructions for areal-project/AReaL, covering agents.md -- areal agent operations guide, quick reference, environment, tests and cli docs.

areal-project/AReaL · 2,812 tokens

AReaL CLAUDE.md

Claude Code instructions for areal-project/AReaL, covering claude.md - areal, what: project overview, why: purpose, how: core commands and check environment.

areal-project/AReaL · 1,697 tokens

Gym AGENTS.md

AGENTS.md instructions for NVIDIA-NeMo/Gym, covering agents.md, quality bar, what this is, architecture and creating environments.

NVIDIA-NeMo/Gym · 2,289 tokens

Gym CLAUDE.md

Claude Code instructions for NVIDIA-NeMo/Gym, a project described as: Evaluate and improve models and agents using environments.

NVIDIA-NeMo/Gym · 3 tokens

xiaozhi-esp32 AGENTS.md

AGENTS.md instructions for 78/xiaozhi-esp32, covering agents.md, project, architecture, required rules and boards and configuration.

78/xiaozhi-esp32 · 1,079 tokens