data-driven-gameplay-design

data-driven-gameplay-design is a skill for Claude Code, Codex from makifbaysal/tasktrooper. It costs 73 tokens per session (1,607 once invoked), scanned A, original, Apache-2.0.

A game-development guide for keeping gameplay settings, items, enemies, abilities, and levels in separate data files instead of hard-coding them. It covers validation, stable IDs, and keeping shared data unchanged while the game runs.

In plain words
What is it for?
Use it when adding or changing game content or tuning values. It helps structure data assets, validate them, connect services, and test rules about the data.
Why use it?
It lets designers change balance values without requiring code changes and reduces errors from invalid or mixed-up data. It also avoids shared global services and makes game rules easier to test.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when adding or changing game content or tuning values. It helps structure data assets, validate them, connect services, and test rules about the data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/makifbaysal/tasktrooper/data-driven-gameplay-design
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.

Any agent
npx skills add makifbaysal/tasktrooper --skill data-driven-gameplay-design
Clone the repo
git clone --depth 1 https://github.com/makifbaysal/tasktrooper

Made for: Claude Code, Codex.

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 data-driven-gameplay-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/data-driven-gameplay-design/github.svg)](https://agentmods.dev/skills/makifbaysal/tasktrooper/data-driven-gameplay-design)
Your own site
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/data-driven-gameplay-design"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/data-driven-gameplay-design/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.

agentmods 80×15 button for data-driven-gameplay-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/data-driven-gameplay-design"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/data-driven-gameplay-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,607 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01607
Opus 5.5 $0.00029 $0.00643
Sonnet 5.5 $0.00015 $0.00321
Haiku 4.5 $0.00007 $0.00161

Measured 4d ago against content hash 957f655e5b82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

data-driven-gameplay-design 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.

catalog/agents/game-developer/skills/data-driven-gameplay-design/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data-Driven Gameplay Design

Overview

Designers balance games by changing numbers hundreds of times. If a number lives in code, each change is a programmer task, a rebuild and a review. If it lives in a data asset, it is an edit a designer can make and a test can check. The code defines what a sword is; the data says what this sword does.

Core principle: Behaviour in code, tuning in data. Data is typed, validated at load, referenced by a stable ID, and never mutated at runtime.

The data asset per engine

// Unity: ScriptableObject definition
[CreateAssetMenu(menuName = "Game/Weapon")]
public sealed class WeaponDefinition : ScriptableObject {
    [SerializeField] string id;
    [SerializeField, Min(0)] int damage = 10;
    [SerializeField, Min(0.05f)] float cooldownSeconds = 0.5f;
    [SerializeField] AnimationCurve falloff = AnimationCurve.Linear(0, 1, 1, 0);
    public string Id => id; public int Damage => damage; public float CooldownSeconds => cooldownSeconds;
    void OnValidate() { if (string.IsNullOrWhiteSpace(id)) Debug.LogError($"{name}: missing id", this); }
}
# Godot: a Resource saved as .tres
class_name WeaponDefinition extends Resource
@export var id: StringName
@export_range(0, 1000) var damage: int = 10
@export_range(0.05, 10.0, 0.05) var cooldown_seconds: float = 0.5
// Unreal: a primary data asset (or an FTableRowBase row in a DataTable imported from CSV)
UCLASS(BlueprintType)
class UWeaponDefinition : public UPrimaryDataAsset {
    GENERATED_BODY()
public:
    UPROPERTY(EditDefaultsOnly, meta = (ClampMin = "0")) int32 Damage = 10;
    UPROPERTY(EditDefaultsOnly, meta = (ClampMin = "0.05")) float CooldownSeconds = 0.5f;
    virtual FPrimaryAssetId GetPrimaryAssetId() const override { return FPrimaryAssetId("Weapon", GetFName()); }
};
// Web: JSON validated once at load (zod)
export const Weapon = z.object({
  id: z.string().min(1),
  damage: z.number().int().nonnegative(),
  cooldownSeconds: z.number().min(0.05),
});
export const weapons = z.array(Weapon).parse(await (await fetch("data/weapons.json")).json());

Read the full file on GitHub · 128 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. 4d ago First seen · 128 lines · 73 tokens per session scan A 957f655e5b82

Subscribe to this mod's changes

data-driven-gameplay-design is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 1,607 once invoked, about $0.0003 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.