agentmods.dev

ai-unity-asset-pipeline

ai-unity-asset-pipeline is a skill for Claude Code, Codex from ezBuilder/code-brain. It costs 95 tokens per session (1,700 once invoked), scanned A, original, Apache-2.0.

A workflow for turning 2D concepts into reusable 3D assets that can be imported into Unity, a game-development tool. It covers image references, mesh creation, Blender processing, and Unity verification.

In plain words
What is it for?
Use it to create vehicles, aircraft, ships, and other game assets; prepare models with pivots, materials, UVs, and detail levels; and export FBX or GLB files for Unity.
Why use it?
It separates asset creation, 3D model cleanup, Unity import, and visual checking so problems can be found at the right stage.

Skill for Claude CodeCodex

not rated 11 6d ago A scan 95 tokens original Apache-2.0
View the source file ezBuilder/code-brain
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.

agentmods
npx agentmods add skills/ezbuilder/code-brain/ai-unity-asset-pipeline
Any agent
npx skills add ezBuilder/code-brain --skill ai-unity-asset-pipeline
Clone the repo
git clone --depth 1 https://github.com/ezBuilder/code-brain

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 ai-unity-asset-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/ezbuilder/code-brain/ai-unity-asset-pipeline.svg)](https://agentmods.dev/skills/ezbuilder/code-brain/ai-unity-asset-pipeline)
Your own site
<a href="https://agentmods.dev/skills/ezbuilder/code-brain/ai-unity-asset-pipeline"><img src="https://agentmods.dev/badge/skills/ezbuilder/code-brain/ai-unity-asset-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00095 $0.01700
Opus 5 $0.00048 $0.00850
Sonnet 5 $0.00019 $0.00340
Haiku 4.5 $0.00010 $0.00170

Measured 5d ago against content hash 218600446196, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-unity-asset-pipeline 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/asset_catalog.py, scripts/asset_pipeline.py, scripts/blender_optimize.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.

kits/global-agent-kit/.claude/skills/ai-unity-asset-pipeline/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI to Unity asset pipeline

Use the installed ai-unity-asset command. Keep provider generation, mesh optimization, Unity import, and live visual proof as separate evidence lanes.

Required flow

  1. Run ai-unity-asset doctor --project "$PWD".
  2. For a new concept, run ai-unity-asset prompt and use ImageGen to create four orthographic views on a plain background. Preserve the generated image, prompt, and fingerprint sidecar as immutable references. Read references/imagegen-prompts.md for fixed prompt fields and bulk rules. For era production, run ai-unity-asset prompt-batch; when ChatGPT To Codex is available, consume its queue exactly as documented in references/chatgpt2codex-asset-factory.md.
  3. Generate a mesh only through a provider the user has authorized. Never read or print API keys. Paid providers and gated model access require explicit approval.
  4. Run Blender normalization: bottom-center pivot, meters, UV preservation, material consolidation, LOD0/LOD1/LOD2, full wheel clearance, and FBX plus GLB export.
  5. Use ai-unity-asset catalog for broad 1950-2999 production. Add an archetype record whenever an existing modular recipe fits; add Python only when a genuinely new topology recipe is required.
  6. Publish into Unity with ai-unity-asset publish or use the complete ai-unity-asset fleet flow for the bundled Transport Tycoon vehicle family.
  7. Verify the manifest, triangle budgets, Unity compilation/tests, and fresh front, rear, side, and elevated Unity renders before claiming success.

Commands

ai-unity-asset doctor --project /absolute/unity/project
ai-unity-asset init --project /absolute/unity/project
ai-unity-asset prompt \
  --asset-id road-city-bus-1988-kr \
  --subject "full-size two-axle city bus" \
  --year 1988 \
  --output /absolute/prompts/road-city-bus-1988-kr.txt
ai-unity-asset prompt-batch \
  --start-year 1950 --end-year 2999 \
  --domain road --region east-asia \
  --output-dir /absolute/output/road-reference-batch
ai-unity-asset gameplay-catalog \
  --start-year 1950 --end-year 2999 \
  --output /absolute/output/transport-gameplay-catalog.json
ai-unity-asset transport-factory \
  --start-year 1950 --end-year 2999 \
  --region global-neutral \
  --output-dir /absolute/output/transport-factory \
  --unity-project /absolute/unity/project
ai-unity-asset fleet \
  --reference /absolute/reference.png \
  --output-dir /absolute/output \
  --unity-project /absolute/unity/project \
  --unity-destination Assets/Resources/Game/Vehicles/Generated
ai-unity-asset optimize --input /absolute/raw.glb --output-dir /absolute/output
ai-unity-asset validate --manifest /absolute/output/asset-manifest.json
ai-unity-asset catalog \
  --start-year 1950 --end-year 2999 \
  --output-plan /absolute/output/asset-production-plan.json

Read the full file on GitHub · 139 lines

Files

What ships with it

14 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. 5d ago First seen · 139 lines · 95 tokens per session scan A 218600446196

Subscribe to this mod's changes

ai-unity-asset-pipeline is a skill published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,700 once invoked, about $0.0005 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.

Creative and mediaGame developmentagent-memoryai-agentsai-toolsautomationclaude-codecode-search
Related

Other skills, from other repositories

kayba-stage-5-action-plan

Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.

kayba-ai/agentic-context-engine · 74 tokens

kayba-stage-2-domain-context

Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.

kayba-ai/agentic-context-engine · 64 tokens

kayba-stage-1-api-analysis

Fetch pre-computed insights from the Kayba API and build a structured summary. Does NOT upload traces or trigger generation — analysis is assumed to already exist. Trigger when the user says "run stage 1", "get insights", "fetch skills", "kayba analyze", or when invoked by the kayba-pipeline orchestrator. Requires the…

kayba-ai/agentic-context-engine · 93 tokens

sprite-gen

Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…

aldegad/sprite-gen · 291 tokens

mnemon

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.

mnemon-dev/mnemon · 25 tokens

mnemon

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.

mnemon-dev/mnemon · 25 tokens