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 skills/thearcforge/uniclaude/unity-workflownpx skills add TheArcForge/UniClaude --skill unity-workflowgit clone --depth 1 https://github.com/TheArcForge/UniClaudeWhat 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 | $0.00040 | $0.00641 |
| Opus 5 | $0.00020 | $0.00320 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
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 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Development Workflow
A lightweight design-first process for Unity features. Follow these phases in order. Do not skip phases — even for tasks that seem simple.
If superpowers:brainstorming is available, prefer that for the design phase — it provides stronger process enforcement. This skill is the fallback when superpowers is not installed.
Phase 1: Analyze
Before doing anything, understand the scope:
- What is the user building? Name the feature in one sentence.
- What existing systems does it touch? Check the scene hierarchy, existing scripts, prefabs.
- What are the unknowns? Identify anything ambiguous in the request.
- Does this need networking, persistence, or live ops integration?
- What is the performance profile? (spawned frequently? rendered every frame? loaded once?)
Ask clarifying questions until there is no ambiguity. Do not proceed with assumptions.
Phase 2: Design
Present your architectural approach before building:
- State which pattern you will use and why (prefab vs variant, SO vs MonoBehaviour, pool vs instantiate).
- Identify the files you will create or modify.
- If multiple systems are involved, sketch the data flow between them.
- Call out tradeoffs explicitly — what you gain and what you give up.
- If the uniclaude:unity-architect skill is available, load it for detailed decision frameworks.
Get explicit user approval before proceeding to implementation.
Phase 3: Implement
Execute the approved design:
- Use MCP tools for all scene, prefab, and asset authoring.
- Write C# scripts for runtime behavior only.
- State what you are doing at each step — do not work silently.
- Use batch operations where possible (scene_setup, component_set_properties, animation_create_controller).
- Wrap script modifications in BeginScriptEditing / EndScriptEditing.
- If the relevant workflow skill is available (uniclaude:scene-authoring, uniclaude:prefab-workflow, uniclaude:animation-workflow), load it for efficient tool sequences.
Phase 4: Verify
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 · 64 lines · 40 tokens per session scan A eb36d8e1949f
unity-workflow is a skill published in the GitHub repository TheArcForge/UniClaude (51 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 641 once invoked, about $0.0002 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.
Other skills, from other repositories
unity-ai-behavior
Use when implementing AI and NPC behavior — state machines, behavior trees, GOAP, NavMesh navigation, decision-making patterns, and when to use each approach.
unity-addressables
Use when managing asset loading — Addressables vs Resources vs direct references, async loading patterns, memory management, group strategies, and content update workflows.
unity-audio
Use when implementing audio systems — audio manager architecture, AudioMixer setup, spatial audio, event-driven audio, music systems, and sound effect management patterns.
unity-performance
Use when analyzing or optimizing Unity performance — CPU/GPU/RAM profiling, object pooling, batching strategies, physics optimization, memory management, and platform-specific budgets.
unity-testing
Use when writing or structuring tests — EditMode vs PlayMode test decisions, test architecture, what to test in Unity, mocking strategies, and CI integration for Unity tests.
animation-workflow
Use when setting up animations — Animator Controllers, Animation Clips, state machines, blend trees, animation events, and Avatar configuration.