unity-workflow

unity-workflow is a command for Claude Code from XeldarAlz/everything-claude-unity. It costs 24 tokens per session (1,328 once invoked), scanned A, original, MIT.

A Unity development command that guides a feature through four phases: clarify requirements, plan the work, execute it with agents, and verify the result with review and tests. It asks for confirmation between phases.

In plain words
What is it for?
Use it for larger Unity features involving systems such as physics, UI, animation, audio, networking, or multiple target platforms.
Why use it?
It turns an incomplete feature request into agreed requirements, an implementation plan, completed changes, and checked results.

Command for Claude Code

Part of the everything-claude-unity plugin — 10 skills, 27 commands, 20 agents, 5 hooks shipped together

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 commands/xeldaralz/everything-claude-unity/unity-workflow
Clone the repo
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unity

Made for: Claude Code.

Or install everything-claude-unity, the plugin that ships this one along with the rest of its 10 skills, 27 commands, 20 agents, 5 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-workflow

README.md
[![agentmods](https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-workflow.svg)](https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-workflow)
Your own site
<a href="https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-workflow"><img src="https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,328 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 $0.00024 $0.01328
Opus 5 $0.00012 $0.00664
Sonnet 5 $0.00005 $0.00266
Haiku 4.5 $0.00002 $0.00133

Measured 3d ago against content hash 3fe77f54481d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-workflow 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 3d 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.

.claude/commands/unity-workflow.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/unity-workflow — Full Development Pipeline

Orchestrate a complete development workflow for: $ARGUMENTS

This command runs a 4-phase pipeline: Clarify → Plan → Execute → Verify. Each phase requires explicit user confirmation before proceeding to the next.

Phase 1: Clarify

Interview the user to build a complete requirements picture. Ask about:

  1. Core mechanic / feature purpose — what does it do? What problem does it solve?
  2. Target platform — mobile (iOS/Android), desktop, WebGL, VR?
  3. Performance constraints — target FPS? Memory budget? Draw call limit?
  4. Unity subsystems involved — physics? UI? animation? audio? networking?
  5. Integration points — what existing systems does this touch?
  6. Acceptance criteria — how do we know it's done? What should we test?

Produce a Requirements Summary with all answers consolidated. Ask the user to confirm before proceeding.

If the user provided a detailed description in $ARGUMENTS and the requirements are clear, you may present the summary directly for confirmation rather than asking each question individually.

Phase 2: Plan

Based on confirmed requirements:

  1. Scan the project — use unity-scout (haiku) for fast codebase exploration: read CLAUDE.md, find relevant existing scripts, map assembly structure
  2. Identify subsystems — which Unity packages and skills are involved?
  3. Assess complexity using the model-routing skill heuristics:
    • Count estimated files to create/modify
    • Check for complexity keywords in the task description
    • Identify risk factors (serialization changes, networking, platform-specific, threading)
    • Rate as simple (1-2 files, no risk) / moderate (3-8 files, some risk) / complex (9+ files, high risk)
  4. Choose execution strategy based on complexity:
    • Simpleunity-coder-lite (sonnet) — faster, cheaper
    • Moderateunity-coder (opus) — deeper reasoning
    • Complex → multiple agents via /unity-team
    • Specialized → route to domain agent: unity-prototyper, unity-ui-builder, unity-network-dev, unity-shader-dev
  5. Generate implementation plan:
    • Scripts to create/modify (with file paths and assembly placement)
    • Scene changes needed (GameObjects, components, physics layers)
    • Dependencies on existing systems
    • Risk areas (serialization, platform-specific, performance)
    • Estimated complexity and chosen agent tier with rationale

Read the full file on GitHub · 135 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. 3d ago First seen · 135 lines · 24 tokens per session scan A 3fe77f54481d

Subscribe to this mod's changes

unity-workflow is a command published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,328 once invoked, about $0.0001 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.