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/xeldaralz/everything-claude-unity/unity-prototypegit clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWhat 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 | $0.00032 | $0.00519 |
| Opus 5 | $0.00016 | $0.00260 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
unity-prototype 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-prototype — Rapid Prototype
Create a playable prototype of: $ARGUMENTS
Workflow
Use the unity-prototyper agent to deliver a complete, playable prototype.
Step 1: Decompose
Break the mechanic into:
- Player systems (movement, abilities, input)
- World elements (platforms, obstacles, triggers)
- Game rules (win/lose, scoring)
- Camera behavior
Step 2: Write Scripts
Create minimal, functional C# scripts:
- Player controller with exposed
[SerializeField]parameters - Game mechanics (physics, triggers, scoring)
- Follow the prototype design principle: functional > clean
Step 3: Build Scene via MCP
Using batch_execute for speed:
- Create a new scene named
Prototype_[MechanicName] - Create all GameObjects (player, environment, obstacles, camera)
- Add and configure components (Rigidbody, Collider, Renderer)
- Set up physics layers and collision matrix
- Configure Cinemachine camera to follow player
Step 4: Verify
- Check console via
read_consolefor any errors - Report the complete prototype setup to the user
Step 5: Report
Tell the user:
- Controls — what keys/buttons to use
- Scripts created — file names and locations
- Scene — name and how to open it
- Tweakable values — which SerializeField parameters to adjust
- Next steps — what to add for a fuller prototype
Step 6: Auto-Verify (Optional)
After the prototype is complete, offer to run the unity-verifier agent:
- Quick review of all prototype scripts for critical issues
- Auto-fix serialization safety, null checks, and performance pitfalls
- Skip architecture concerns (prototypes prioritize speed over structure)
Suggest: "Prototype ready! Want me to run a quick verification pass?"
Design Rules
- 10-minute target — if it takes longer, you're overbuilding
- Placeholder visuals — colored primitives, no art needed
- Everything tweakable — SerializeField with Headers
- Single scene — no multi-scene for prototypes
- No UI — use Debug.Log and Gizmos for feedback
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 · 32 tokens per session scan A 45cf4331dd68
unity-prototype is a command published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 519 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 commands, from other repositories
become
Agent crystallization command. Studies a tool, role, or person and produces a portable 9-section agent that inhabits the domain - with beliefs, scar tissue, and instincts.
notebook
Low-ceremony capture for ideas (half-formed, want to mature into stories), todos (concrete actions), and notes (durable project/team facts for future recall). One-line capture, conditional elaboration AUQ. Use BEFORE thoughts get forced into stories.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.
cycle-start
Activate a cycle and start implementing its stories.
story-continue
Resume an interrupted story from where you left off.
story-archive
Move a story from a cycle back to the backlog.