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.
npx agentmods add commands/devdavv/unity-ai-workflow/uw-cmd-setup-projectgit clone --depth 1 https://github.com/devdavv/unity-ai-workflowWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00769 |
| Opus 5 | $0.00000 | $0.00385 |
| Sonnet 5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
uw-cmd-setup-project 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/uw-cmd-setup-project — Project Setup Workflow
Initialize a new Unity project with all infrastructure: folders, packages, git, and MCP connections.
Skills
Load uw-unity-project-setup skill from .claude/skills/uw-unity-project-setup/SKILL.md.
Steps
0. Select Dev Mode
Ask the user before anything else:
"Which dev mode do you want for this project?
- Guided (recommended default) — We collaborate. I suggest next steps and execute after you confirm key decisions.
- Autonomous — Tell me your game idea and goals, I'll build the game with minimal interruptions. For best results, also enable Claude Code auto mode.
You can change it later in
docs/ProjectConfig.yaml -> ai_mode."
If autonomous mode: Ask ALL onboarding questions now (pitch, platforms, genre, references, features, packages, MCP availability). Set ai_mode in ProjectConfig.
1. Verify Environment
- Confirm Unity version matches ProjectConfig.
- Ask about MCP availability (Unity MCP, GitHub MCP).
- If install links needed, reference
docs/MCP_SETUP.md— never guess URLs. - Update
docs/ProjectConfig.yaml -> mcpsection.
2. Create Folder Structure
Use uw-unity-project-setup skill:
- Create
Assets/_Project/with standard subfolders. - Structure depends on
folder_strategyfrom ProjectConfig. - Create
Core.asmdefin root scripts folder. - Create
Core.Tests.EditMode.asmdefinTests/EditMode/so the test runner skill has a test assembly from day one.
3. Install Packages
From docs/ProjectConfig.yaml -> packages:
- Via Unity MCP
manage_packagesif available. - Manual fallback (no MCP): Write an editor script using
UnityEditor.PackageManager.Client.Add()to install packages programmatically from a menu item. The user runs it once, then it can be deleted. - Install third-party from
docs/ProjectConfig.yaml -> third_party.
4. Configure Editor Settings
Via Unity MCP if available:
- Render pipeline (URP/HDRP/Built-in)
- Color space: Linear
- Scripting backend: IL2CPP
- Target platform(s)
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.
- 2d ago First seen · 82 lines · 0 tokens per session scan A 03359240ab03
uw-cmd-setup-project is a command published in the GitHub repository devdavv/unity-ai-workflow (41 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 769 tokens. 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.
Other commands, from other repositories
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
cert-check
Review the current state against certification and platform compliance expectations.
combat-design
Design or revise combat rules, variables, readability, and tuning direction.
context
Activate a project phase context and align agents, commands, and priorities to it.
liveops-brief
Create a concise live operations brief for an event, offer, patch, or campaign.
adopt
Brownfield onboarding audit and migration plan.