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 skills add makifbaysal/tasktrooper --skill game-engine-choicegit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/skills/makifbaysal/tasktrooper/game-engine-choice)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/game-engine-choice"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-engine-choice/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/skills/makifbaysal/tasktrooper/game-engine-choice"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/game-engine-choice.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 | $0.00059 | $0.02171 |
| Opus 5.5 | $0.00024 | $0.00868 |
| Sonnet 5.5 | $0.00012 | $0.00434 |
| Haiku 4.5 | $0.00006 | $0.00217 |
Grade A, and why
game-engine-choice 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Engine Choice
Overview
Choosing an engine is a one-way door: assets, scenes, scripts, editor tooling and the team's skills all bind to it. On an existing project there is nothing to choose — the engine and the exact editor version in the repository are the answer. The choice only opens for a brand-new game (or when the analiz task explicitly decides it), and then it is made from the target platforms first, not from preference.
Core principle: The repository's engine and pinned version win. For a new game, the platform list decides most of the choice before taste gets a vote.
Step 1 — read what the repository already says
| Signal | Engine | Version lives in |
|---|---|---|
ProjectSettings/ProjectVersion.txt |
Unity | m_EditorVersion: 6000.3.xf1 |
project.godot |
Godot | config/features=PackedStringArray("4.7", ...); a .csproj beside it means Godot .NET |
*.uproject |
Unreal Engine | "EngineAssociation": "5.6" (a GUID means a source build) |
package.json with phaser, pixi.js, three, @babylonjs/core, playcanvas, excalibur, kaplay |
web engine | the lockfile's resolved version |
Cargo.toml with bevy |
Bevy | Cargo.lock — the minor version is the API |
game.project |
Defold | [project] / bob.jar version in CI |
.csproj referencing MonoGame.Framework.* |
MonoGame | the package version |
pygame / pygame-ce in pyproject.toml / requirements.txt |
pygame | the pin |
Found one? Stop here and use it. Never open the project in a different editor version: Unity and Unreal re-serialize assets on open and Godot rewrites project.godot and import files, producing a diff nobody asked for.
Step 2 — only for a new game
digraph e {
"Repo already has an engine?" [shape=diamond];
"Use it, at its pinned version" [shape=box];
"Console or high-end 3D required?" [shape=diamond];
"Unreal (AAA-style 3D) or Unity" [shape=box];
"Browser is the main target?" [shape=diamond];
"Web stack: Phaser / PixiJS (2D), three.js / Babylon.js / PlayCanvas (3D)" [shape=box];
"Rust team, code-first, accepts churn?" [shape=diamond];
"Bevy" [shape=box];
"Godot (2D or mid-scope 3D) or Unity (mobile, broad platform reach)" [shape=box];
"Repo already has an engine?" -> "Use it, at its pinned version" [label="yes"];
"Repo already has an engine?" -> "Console or high-end 3D required?" [label="no"];
"Console or high-end 3D required?" -> "Unreal (AAA-style 3D) or Unity" [label="yes"];
"Console or high-end 3D required?" -> "Browser is the main target?" [label="no"];
"Browser is the main target?" -> "Web stack: Phaser / PixiJS (2D), three.js / Babylon.js / PlayCanvas (3D)" [label="yes"];
"Browser is the main target?" -> "Rust team, code-first, accepts churn?" [label="no"];
"Rust team, code-first, accepts churn?" -> "Bevy" [label="yes"];
"Rust team, code-first, accepts churn?" -> "Godot (2D or mid-scope 3D) or Unity (mobile, broad platform reach)" [label="no"];
}
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.
- 4d ago First seen · 122 lines · 59 tokens per session scan A 03f252073329
game-engine-choice is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 2,171 once invoked, about $0.0002 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 2026-10-09.
Other skills, from other repositories
i4h-workflow-train-rl
Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
openclaw-plugin
You are an autonomous agent in a persistent world. Your character is in SOUL.md. World rules are in WORLD.md.
architecture-design
Use this skill to design system architecture with documented trade-offs and decisions before any implementation begins. Activates when a feature, system, or component requires non-trivial structural decisions about how components interact, what data stores to use, or how to decompose a problem.
repository-discovery
Use this skill to systematically explore an unfamiliar codebase before making any changes. Activates when starting work in an unknown repository, adding a new feature, debugging without prior context, or when no CONTEXT.md exists. Produces a grounded understanding of architecture, conventions, and constraints.
rapid-prototyping
Use this skill to build disposable, rapid proof-of-concept prototypes and spikes to test feasibility, validate API designs, or explore library capabilities before committing to a full production architecture.