What is uw-cmd-create?

A code-creation workflow for Unity utilities, helpers, data classes, editor tools, and backend systems. It uses test-driven development (TDD), where tests are written before the code they check.

Use it to scaffold feature folders and test assemblies, convert Gherkin scenarios into NUnit tests, and write the minimum code needed to make those tests pass.

It provides a repeatable way to turn a requirement into a small, tested implementation. This helps catch mistakes early and keeps the code within the project's architecture rules.

uw-cmd-create — Command by devdavv

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/devdavv/unity-ai-workflow/uw-cmd-create

Clone the repo

git clone --depth 1 https://github.com/devdavv/unity-ai-workflow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 471 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00471
Opus 5	$0.00000	$0.00235
Sonnet 5	$0.00000	$0.00094
Haiku 4.5	$0.00000	$0.00047

Measured 2d ago against content hash aaa3af67db88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

uw-cmd-create 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.

.claude/commands/uw-cmd-create.md · 54 lines

What it actually says

/uw-cmd-create — Code Creation Workflow

Generate isolated code following a test-driven development approach.

Scope: Utilities, helpers, data classes, editor tools, and backend systems with no direct game feel. For gameplay features: use /uw-cmd-implement-feature instead.

Skills

Load uw-unity-feature-scaffold from .claude/skills/uw-unity-feature-scaffold/SKILL.md. Load uw-unity-test-runner from .claude/skills/uw-unity-test-runner/SKILL.md.

Steps

1. Understand the Requirement

Which GDD scenario does this implement?
Read the relevant TDD section for architecture constraints.
Check docs/ProjectConfig.yaml for package versions and technology choices.

2. Scaffold the Feature

Use uw-unity-feature-scaffold skill:

Feature folder structure
Assembly Definition (.asmdef)
Test Assembly Definition

3. Write Tests First

Use uw-unity-test-runner skill:

Convert the Gherkin scenario to NUnit test(s).
Write the test — it should fail because the implementation doesn't exist yet.

4. Implement

Write the minimal code to make tests pass:

Follow CLAUDE.md rules (serialization, caching, thread safety)
Follow docs/CODING_STANDARDS.md formatting
Follow docs/NAMING_CONVENTIONS.md for identifiers
Use GameDebug for debug logging
If creating SO data/events, follow uw-scriptable-object-arch patterns
If creating DI services, follow uw-dependency-injection patterns (when architecture_pattern: "di-first")

5. Run Tests

Via Unity MCP run_tests if available.
Otherwise, instruct user to run in Test Runner.
All tests must pass before proceeding.

6. Commit

Feature branch: feature/{feature-name}
Commit message: feat({feature}): {description}
Follow docs/GIT_CONVENTIONS.md

7. Output

Working feature with passing tests
Feature committed to a branch

$ARGUMENTS

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.

2d ago First seen · 54 lines · 0 tokens per session scan A aaa3af67db88

Subscribe to this mod's changes

uw-cmd-create 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 471 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.

Backend and APIs Game development Testing ai-workflow antigravity-ide claude-code game-development unity unity2d

uw-cmd-create

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/uw-cmd-create — Code Creation Workflow

Skills

Steps

1. Understand the Requirement

2. Scaffold the Feature

3. Write Tests First

4. Implement

5. Run Tests

6. Commit

7. Output

What this file has done since we first saw it

Other commands, from other repositories

unity-placeholders

combat-design

godot-review

level-beat

adopt

OPSX: Explore