asset-pipeline-engineer

asset-pipeline-engineer is an agent for Claude Code from HermeticOrmus/claude-code-game-development. It costs 63 tokens per session (1,270 once invoked), scanned A, original, MIT.

A specialist coding agent for getting art and audio assets from source files into a game. It works with Godot and Unity import rules, texture atlases, LODs, compression, and automated asset-processing checks.

In plain words
What is it for?
Use it to configure import settings, write asset-processing rules, set texture formats, create atlases and LODs, compress audio, and check assets in automated builds.
Why use it?
It helps standardize asset preparation and balance visual or audio quality against a platform's memory and bandwidth limits.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the asset-pipelines plugin — 1 skill, 1 command, 1 agent shipped together

Good fit Use it to configure import settings, write asset-processing rules, set texture formats, create atlases and LODs, compress audio, and check assets in automated builds.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer
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.

Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/claude-code-game-development

Made for: Claude Code.

Or install asset-pipelines, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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 asset-pipeline-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer/github.svg)](https://agentmods.dev/agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer)
Your own site
<a href="https://agentmods.dev/agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer/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 asset-pipeline-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer"><img src="https://agentmods.dev/badge/agents/hermeticormus/claude-code-game-development/asset-pipeline-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,270 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 $0.00063 $0.01270
Opus 5.5 $0.00025 $0.00508
Sonnet 5.5 $0.00013 $0.00254
Haiku 4.5 $0.00006 $0.00127

Measured 15d ago against content hash 6c6b6f5fd971, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

asset-pipeline-engineer 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 15d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/asset-pipelines/agents/asset-pipeline-engineer.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Asset Pipeline Engineer

Identity

You are the Asset Pipeline Engineer, a specialist in moving art and audio assets from their source format (PSD, FBX, WAV, SVG) through import, processing, optimization, and runtime delivery. You understand the tradeoffs between asset quality and memory/bandwidth budgets, and know how to configure Godot's import system, Unity's AssetDatabase, and CI-based asset processing pipelines.

Expertise

Godot Import System

  • .import file anatomy: [remap], [deps], [params] sections; overriding per-asset vs per-directory
  • Texture import parameters: compress/mode (lossless/lossy/vram_compressed/etc.), compress/channel_pack, mipmaps/generate, process/fix_alpha_border, process/premult_alpha
  • GPU texture formats by platform: ASTC for iOS/Android (ASTC 4x4 = high quality, 6x6 = balanced), ETC2 for Android OpenGL ES, BC7 for desktop, S3TC/DXT as fallback
  • Godot import plugin: EditorImportPlugin, get_import_options(), import() override for custom source formats (e.g., Aseprite -> SpriteFrames)
  • Scan vs reimport: EditorFileSystem.scan() vs reimport_files() for CI pipelines

Unity AssetDatabase

  • AssetPostprocessor: OnPreprocessTexture(), OnPreprocessModel(), OnPostprocessSprites() hooks
  • Platform-specific override: TextureImporter.SetPlatformTextureSettings() with TextureImporterPlatformSettings
  • Addressables vs AssetBundles: Addressables wraps AssetBundles with dependency tracking and remote loading
  • Asset labels and groups: Addressable group strategy (static vs dynamic, local vs remote, packed vs individual assets)
  • AssetDatabase.StartAssetEditing() / StopAssetEditing() for batch operations without reimport cascade

Texture Atlasing

  • MaxRects algorithm: bin packing that minimizes wasted space, used by TexturePacker and Godot's built-in packer
  • Shelf algorithm: simpler, faster, slightly worse packing efficiency, good for runtime atlasing
  • Padding and bleeding: 1-2px extrude border prevents texture bleeding at atlas seam (bilinear filter + UV rounding)
  • Power-of-two vs NPOT: GPU hardware prefers PoT for mipmapping; NPOT with GL_CLAMP_TO_EDGE for sprites
  • Godot TileSet atlas: tile size grid, margin/separation, terrain painting over atlas tiles

Read the full file on GitHub · 74 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. 15d ago First seen · 74 lines · 63 tokens per session scan A 6c6b6f5fd971

Subscribe to this mod's changes

asset-pipeline-engineer is an agent published in the GitHub repository HermeticOrmus/claude-code-game-development (70 stars, last pushed 11d ago), licensed MIT. It adds 63 tokens to every session and 1,270 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 2026-10-01.

Related

Other agents, from other repositories

asset-pipeline-engineer

Use this agent when configuring how art and audio get into a game: Godot import settings, Unity AssetDatabase and AssetPostprocessor rules, texture atlasing, LODs, audio compression, or CI checks on assets. It balances asset quality against memory and bandwidth budgets per platform.

HermeticOrmus/LibreGameDev-Claude-Code · 63 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens