unity-subagent-dev

unity-subagent-dev is a skill for Claude Code from sonereraslan/local-marketplace. It costs 98 tokens per session (1,568 once invoked), scanned A, original, MIT.

A Unity development workflow that assigns each planned task to a fresh coding subagent, then reviews the result for requirements and Unity code quality. Unity is a game engine and development environment.

In plain words
What is it for?
Executing mostly independent Unity implementation tasks from a plan, with testing and two review stages after each task.
Why use it?
It separates implementation from review and checks both whether the task matches the plan and whether the Unity code follows stated design principles.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the superunity plugin — 11 skills, 1 command, 4 agents, 2 hooks shipped together

Good fit Executing mostly independent Unity implementation tasks from a plan, with testing and two review stages after each task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonereraslan/local-marketplace/unity-subagent-dev
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 sonereraslan/local-marketplace --skill unity-subagent-dev
Clone the repo
git clone --depth 1 https://github.com/sonereraslan/local-marketplace

Made for: Claude Code.

Or install superunity, the plugin that ships this one along with the rest of its 11 skills, 1 command, 4 agents, 2 hooks.

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 unity-subagent-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonereraslan/local-marketplace/unity-subagent-dev.svg)](https://agentmods.dev/skills/sonereraslan/local-marketplace/unity-subagent-dev)
Your own site
<a href="https://agentmods.dev/skills/sonereraslan/local-marketplace/unity-subagent-dev"><img src="https://agentmods.dev/badge/skills/sonereraslan/local-marketplace/unity-subagent-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,568 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 $0.00098 $0.01568
Opus 5 $0.00049 $0.00784
Sonnet 5 $0.00020 $0.00314
Haiku 4.5 $0.00010 $0.00157

Measured 8d ago against content hash 4538dd3b9966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

unity-subagent-dev 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 8d 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.

plugins/superunity/skills/unity-subagent-dev/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development (Unity)

Execute plan by dispatching a fresh subagent per task, with two-stage review after each: spec compliance first, then Unity code quality.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.

Senior Unity principles enforced:

  • Architecture consistency over local optimization
  • Composition over inheritance (especially for MonoBehaviours)
  • Isolate pure C# domain logic from Unity-specific glue code
  • Minimize hidden coupling (no implicit scene dependencies)
  • Validate runtime behavior, not just compilation
  • Avoid premature abstraction, but always leave extension points

When to Use

  • Have an implementation plan with mostly independent tasks
  • Want to stay in this session (vs. parallel session with unity-executing-plans)
  • Want fresh subagent per task (no context pollution) with two-stage review

The Process

  1. Read plan, extract tasks, restate architectural intent, create task list
  2. For each task: a. Dispatch implementer subagent (read and fill ./implementer-prompt.md) b. If implementer asks questions, answer them, then re-dispatch c. Implementer implements, tests, stages files, self-reviews d. Dispatch spec reviewer (read and fill ./spec-reviewer-prompt.md) e. If not spec compliant, implementer fixes gaps, re-review f. Dispatch code quality reviewer (read and fill ./code-quality-reviewer-prompt.md) g. If not quality approved, implementer fixes issues, re-review h. Mark task complete
  3. After all tasks: dispatch final reviewer for entire implementation
  4. Invoke superunity:unity-finishing-branch

Prompt Templates

Before dispatching any subagent, read the corresponding prompt template file and fill in all bracketed placeholders with actual task content.

  • ./implementer-prompt.md — Dispatch implementer subagent
  • ./spec-reviewer-prompt.md — Dispatch spec compliance reviewer subagent
  • ./code-quality-reviewer-prompt.md — Dispatch code quality reviewer subagent

Read the full file on GitHub · 161 lines

Files

What ships with it

3 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. 8d ago First seen · 161 lines · 98 tokens per session scan A 4538dd3b9966

Subscribe to this mod's changes

unity-subagent-dev is a skill published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 98 tokens to every session and 1,568 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 2026-08-31.