agentmods.dev

game-dev-agent

game-dev-agent is a skill for Claude Code from MelonS/MelonS-Agents. It costs 46 tokens per session (1,024 once invoked), scanned A, original, MIT.

An AI assistant for Unity, a tool for building games, covering game code, visual assets, audio, balance settings, and events that happen during play.

In plain words
What is it for?
It is for creating sprites and icons, scaffolding Unity scripts, tuning game parameters, preparing audio files, and generating in-game events.
Why use it?
It brings several game-development jobs into one workflow, including Unity-specific C# code and changes to game settings.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

not rated 17repo 2mo ago A scan SkillSpector: pass 46 tokens original MIT

Good fit It is for creating sprites and icons, scaffolding Unity scripts, tuning game parameters, preparing audio files, and generating in-game events.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/melons/melons-agents/game-dev-agent
View source ↗ MelonS/MelonS-Agents melons.github.io
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 MelonS/MelonS-Agents --skill game-dev-agent
Clone the repo
git clone --depth 1 https://github.com/MelonS/MelonS-Agents

Made for: Claude Code.

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 game-dev-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/melons/melons-agents/game-dev-agent/github.svg)](https://agentmods.dev/skills/melons/melons-agents/game-dev-agent)
Your own site
<a href="https://agentmods.dev/skills/melons/melons-agents/game-dev-agent"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/game-dev-agent/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 game-dev-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/melons/melons-agents/game-dev-agent"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/game-dev-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,024 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00046 $0.01024
Opus 5.5 $0.00018 $0.00410
Sonnet 5.5 $0.00009 $0.00205
Haiku 4.5 $0.00005 $0.00102

Measured 2mo ago against content hash bc632dd402f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

game-dev-agent 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.

The scan reads SKILL.md. This mod also ships 17 executable files (scripts/agent.py, scripts/latest_build.py, scripts/modules/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/game-dev-agent/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

game-dev-agent

AI agent that orchestrates Unity game development tasks via CLI. Companion to pawnsim (the actual game built using this agent).

What it does

Modules (each = subagent):

  • asset_gen — Generate sprites / tiles / UI icons via ComfyUI + SDXL, auto-save to Unity Assets folder with proper import settings
  • code_assist — Unity-aware C# scaffolding: MonoBehaviour / ScriptableObject / Editor scripts. Knows Unity 2022.3 API.
  • balance_tune — Read ScriptableObject configs + JSON balance files, propose parameter tuning. Game-dev specific (beyond what general AI code assistants do).
  • audio_gen — BGM via Suno (operator-provided files), SFX via local AudioCraft / freesound API. Auto-conform to Unity AudioClip import.
  • runtime_director (in-game AI) — LLM-driven event generation for the game itself, demonstrating dev-time + runtime AI agent patterns.

Why this skill matters

Career positioning: combines deep game-dev domain (operator's existing strength) with AI agent engineering (rare, emerging hire-niche). Portfolio = (this agent) + (game built with it) = T-shape proof.

Operator-specific:

  • Operator has 10+ year game dev background
  • AI agent engineer roles emerging in game industry + general tech
  • Game industry downturn — pure game-dev roles competitive
  • AI agent angle = downturn-resilient niche

Usage (planned, Day 1)

# Generate a sprite
python skills/game-dev-agent/scripts/agent.py gen-sprite \
    "evil knight enemy, 2D pixel art, top-down view, simple silhouette" \
    --output Assets/Sprites/enemy_knight.png

# Scaffold Unity MonoBehaviour script
python skills/game-dev-agent/scripts/agent.py code \
    "PlayerMovement: top-down 2D, WASD input, 5 m/s speed" \
    --output Assets/Scripts/PlayerMovement.cs

# Analyze + propose balance changes
python skills/game-dev-agent/scripts/agent.py balance \
    --config Assets/Configs/enemies.json \
    --goal "make wave 5 challenging but beatable"

# Generate BGM via Suno (operator provides Suno prompt template)
python skills/game-dev-agent/scripts/agent.py audio \
    --style "lofi dungeon synth, slow, atmospheric" \
    --output Assets/Audio/BGM_dungeon.mp3

Read the full file on GitHub · 117 lines

Files

What ships with it

38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 117 lines · 46 tokens per session scan A bc632dd402f0

Subscribe to this mod's changes

game-dev-agent is a skill published in the GitHub repository MelonS/MelonS-Agents (17 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,024 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 2026-08-30.

Autonomous AgentsClaude CodeGame developmentagentskillsai-agentsautomationcolony-sim
Related

Other skills, from other repositories

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

ascii-city-engine

Build portable, first-person colored ASCII city engines and small GIS-derived city packs. Use when designing terrain-following walking, raycast character rendering, city-provider schemas, or reproducible public-GIS ingestion. Do not use for conventional 3D/WebGL games, multi-level interiors, general GIS analysis, or…

magnus919/agent-skills · 72 tokens

bevy-ecs-patterns

Use when writing Bevy (Rust ECS) game code - pin and respect the repo's minor version, plugins/systems/queries/resources, schedules with FixedUpdate and Time, states and run conditions, messages vs observers across versions, required components, testing systems with App::update and a manual time strategy, compile-time…

makifbaysal/tasktrooper · 74 tokens

game-engine-choice

Use when a game task could run on more than one engine or the repository has no engine yet - read the repo's engine and pinned version, and only for a brand-new game pick one from platforms, 2D/3D, team language, scale and licensing.

makifbaysal/tasktrooper · 59 tokens

game-networking

Use when touching multiplayer code - authoritative server, client prediction and reconciliation, interpolation, lockstep and rollback, server-side validation of every RPC per engine (Netcode, Unreal replication, Godot multiplayer, Colyseus, Bevy crates), bandwidth and versioned messages.

makifbaysal/tasktrooper · 58 tokens

game-visual-self-review

Use when you are about to hand off a change a player can see - the exact steps to look at it running (web game in the browser at two viewports plus a seeded Playwright smoke run for input and console errors; engine games through a headless frame capture), the checklist, and how to report what could not be observed.

makifbaysal/tasktrooper · 74 tokens