unity-init

unity-init is a command for Claude Code from XeldarAlz/everything-claude-unity. It costs 29 tokens per session (377 once invoked), scanned A, original, MIT.

A Unity project setup command that scans the project and creates or updates a tailored CLAUDE.md instruction file. It records the Unity version, packages, render pipeline, code structure, and scenes it finds.

In plain words
What is it for?
Use it when starting work on an unfamiliar Unity project or after its packages and structure have changed. It helps document installed tools, code modules, scenes, project rules, and suggested skills.
Why use it?
It removes the need to document a Unity project by hand and helps the coding agent understand the project's existing setup before making changes.

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-init
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.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 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 $0.00029 $0.00377
Opus 5 $0.00015 $0.00188
Sonnet 5 $0.00006 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 3d ago against content hash f12a6810e7ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-init 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-init.md · 44 lines

What it actually says

/unity-init — Project Setup

Scan this Unity project and generate a tailored CLAUDE.md configuration.

Steps

  1. Read project info via MCP project_info resource to get Unity version, platform, and state.

  2. Scan Packages/manifest.json to detect installed packages:

    • Render pipeline (URP, HDRP, or Built-in)
    • Input System, Addressables, Cinemachine, Timeline, TextMeshPro
    • Networking (Netcode, Mirror, Photon, Fish-Net)
    • Third-party (DOTween, UniTask, VContainer, Zenject, Odin)
  3. Scan for assembly definitions (.asmdef files) — map the project's assembly structure.

  4. Scan for scenes — list all .unity files in Assets/.

  5. Check existing CLAUDE.md — if one exists, preserve user customizations.

  6. Generate CLAUDE.md with:

    • Project overview (Unity version, render pipeline, detected packages)
    • Assembly structure
    • Scene list
    • References to rules files (.claude/rules/*.md)
    • Recommended skills based on detected packages
    • MCP integration notes
    • Key conventions summary
  7. Report what was detected and configured. Suggest next steps:

    • Review and customize the generated CLAUDE.md
    • Install unity-mcp if not already present
    • Try /unity-audit for a full project health check

Output

Present the results in a clear summary table showing what was detected and which skills are recommended.

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 · 44 lines · 29 tokens per session scan A f12a6810e7ca

Subscribe to this mod's changes

unity-init is a command published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 377 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.