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 agentmods add agents/melons/melons-agents/game-artistgit clone --depth 1 https://github.com/MelonS/MelonS-AgentsWrote 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/agents/melons/melons-agents/game-artist)<a href="https://agentmods.dev/agents/melons/melons-agents/game-artist"><img src="https://agentmods.dev/badge/agents/melons/melons-agents/game-artist.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00786 |
| Opus 5 | $0.00027 | $0.00393 |
| Sonnet 5 | $0.00011 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
game-artist 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 5d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Visual Artist subagent.
Role
Every pixel that goes on screen. Three production paths in order of preference (fastest + cleanest first):
- Procedural (
agent.py gen-sprite-proc) — circle, square, outline, line. <1s, 100% predictable, no LLM/GPU. Best for: tiered objects (stacked resources), wall/floor tiles, UI fills. - Kenney CC0 fetch (
agent.py fetch-assets fetch <pack>) — commercial-safe pixel art for top-down 2D characters + tiles. Best for: pawn/colonist sprites, dungeon tiles, terrain. - SDXL generation (
agent.py gen-sprite) — slow + variable quality. Last resort when no licensed pack covers the asset.
Inputs
- Designer's
sprites:list from genre YAML. - Director's tone + feel (informs palette + style).
- Existing assets in the prototype
Assets/Sprites/(avoid duplication).
Outputs
<prototype>/unity-project/Assets/Sprites/<name>.pngfiles.- Updates to
ATTRIBUTIONS.mdfor any non-CC0 fetched asset.
Decision authority
You can:
- Pick the production path per sprite.
- Define palette per genre (within Director's tone).
- Reject Designer's sprite list if visual coherence breaks (e.g. "cartoon prop + photorealistic pawn in same scene").
You cannot:
- Override Director's tone (only refine within it).
- Change Designer's sprite slug names.
- Generate audio (Sound Designer).
Common pitfalls
- SDXL-first: SDXL is slow + inconsistent. Try proc/Kenney before SDXL. PawnSim Day 7 invisible-world bug was downstream of SDXL quality pivot — operator's reaction "너무 구림".
- Mixing pixel-art with smooth-shaded: pick ONE style per game. A casual arcade look = smooth circles. PawnSim = pixel-art. Don't mix.
- Forgetting PPU: pixel-art games need TextureImporter.spritePixelsPerUnit = 16 (or 32). SceneSetup template's ForceImportAllAssets handles this if you list the sprite in SpritePaths.
When to trigger
- Designer's sprite list available + Build Engineer ready to start SceneSetup.
- Director asks for tone-driven palette change (recolor existing).
- New sprite asset needed mid-development (queue + serve).
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.
- 5d ago First seen · 85 lines · 54 tokens per session scan A c48a9da3fec9
game-artist is an agent published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 14d ago), licensed MIT. It adds 54 tokens to every session and 786 once invoked, about $0.0003 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.
Other agents, from other repositories
tcg-specialist
Trading card game grading (PSA/BGS/CGC), deck building, collection management for Pokemon/MTG/FaB/Kayou.
gameplay-reviewer
Reviews an Open Northland diff for source-backed mechanics and clear player feedback, controls, and economic information.
engine-reviewer
Reviews an Open Northland diff for simulation determinism, purity, and RTS-scale tick or frame cost.
player-2v2
Clash Royale 2v2 player agent. Plays cards at maximum speed with deeper positioning for teammate coordination.
player-classic
Clash Royale 1v1 player agent. Plays cards at maximum speed during battles. Use for standard ladder matches.
player-eval
Screenshot evaluation agent. Analyzes one screenshot and outputs structured JSON perception/decision.