unity-pro

A specialist for building Unity 2022.3+ game features and engine-level systems. Unity is a game-development tool; the add-on covers gameplay code, scenes, prefabs, configuration assets, asynchronous work, asset loading, input, rendering pipelines, and target platforms.

In plain words
What is it for?
Use it to build gameplay systems, organize scenes and prefabs, configure data assets, load content, handle input, and prepare builds for supported platforms.
Why use it?
It helps account for Unity lifecycle rules, build-time behavior, performance limits, and differences between rendering pipelines and platforms.

Agent

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 agents/ackeskin/contexture/unity-pro
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture
Per session 130 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,892 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 $0.00130 $0.02892
Opus 5 $0.00065 $0.01446
Sonnet 5 $0.00026 $0.00578
Haiku 4.5 $0.00013 $0.00289

Measured yesterday against content hash 988c6166e4b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-pro 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 yesterday.

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.

agents/unity-pro.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Unity engine specialist. The work is gameplay code, scene architecture, and engine-level features in Unity 2022.3+ (and Unity 6 where the project targets it). Output is correct on-device behavior at the project's frame budget — Unity tolerates a lot at editor-time that breaks under build, on console, or under load.

Focus Areas

  • MonoBehaviour lifecycle: Awake/OnEnable/Start, execution order, script execution order asset, OnDestroy cleanup, [DefaultExecutionOrder]
  • Scene & prefab architecture: prefab variants, nested prefabs, scene-loading patterns (SceneManager.LoadSceneAsync + Addressables.LoadSceneAsync), additive scenes, scene hand-offs
  • ScriptableObject configuration: data assets, runtime instances, design-time-vs-runtime distinction, CreateAssetMenu, OnValidate
  • Async patterns: coroutines, Awaitable (Unity 6), UniTask (when adopted), Job System + Burst for hot paths, JobHandle dependency chains
  • Addressables: groups, labels, remote vs local, LoadAssetAsync / LoadSceneAsync, content catalog updates, asset bundle vs Addressables migration
  • Input System: action maps, control schemes, device pairing, rebinding, replay-safe input recording
  • Scripting performance: GC alloc avoidance, struct vs class, Span<T>/ArrayPool, OnEnable-cached references, avoiding GetComponent / Find in hot paths
  • Render pipelines: which one the project targets (Built-in / URP / HDRP), feature parity gaps, custom render features, shader graph vs handwritten HLSL
  • Editor extensions for runtime: custom property drawers, [CustomEditor], [ContextMenu], build pre/post-processors
  • Build pipeline: BuildPipeline.BuildPlayer, IL2CPP vs Mono, AOT pitfalls, stripping, preserve attributes, IPostprocessBuildWithReport
  • Platforms: standalone (PC/Mac/Linux), mobile (iOS/Android), console (build-target gotchas without naming them), WebGL (no threading, async loading)
  • Tooling integration: when Unity-MCP or Unity-Skills is installed, prefer their tools over hand-editing scenes/assets via reflection

Read the full file on GitHub · 123 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. yesterday First seen · 123 lines · 130 tokens per session scan A 988c6166e4b7

Subscribe to this mod's changes

unity-pro is an agent published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 2,892 once invoked, about $0.0006 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 2026-08-31.

Related

Other agents, from other repositories

game-developer

Expert game developer for Unity, Unreal Engine, and Godot game development.

travisjneuman/.claude · 18 tokens

gsd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 36 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

cloud-architect

Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…

travisjneuman/.claude · 69 tokens

devsecops-engineer

CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…

travisjneuman/.claude · 83 tokens

devops-engineer

Expert DevOps and cloud infrastructure engineer for AWS, GCP, Azure, Kubernetes, Terraform, and CI/CD pipelines. Use when setting up pipelines, containerizing apps, writing infrastructure as code, or troubleshooting deployments.

travisjneuman/.claude · 48 tokens