unity-build

unity-build is a skill for Claude Code, Codex from ToshikiImagawa/unity-claude-code-tools. It costs 27 tokens per session (749 once invoked), scanned A, original, MIT.

A workflow for validating a Unity project build and interpreting the results. It supports both batch mode, where the Editor is closed, and Editor mode, where Unity is already open.

In plain words
What is it for?
Use it when building a Unity project, checking script compilation, testing while the Editor is open, or validating a target such as Windows, Android, iOS, or WebGL.
Why use it?
It selects the appropriate validation method and turns build output into a clear success or error report instead of leaving you to interpret raw logs.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the unity-tools-plugin plugin — 2 skills, 2 commands, 2 agents, 1 MCP server 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 skills/toshikiimagawa/unity-claude-code-tools/unity-build
Any agent
npx skills add ToshikiImagawa/unity-claude-code-tools --skill unity-build
Clone the repo
git clone --depth 1 https://github.com/ToshikiImagawa/unity-claude-code-tools

Made for: Claude Code, Codex.

Or install unity-tools-plugin, the plugin that ships this one along with the rest of its 2 skills, 2 commands, 2 agents, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for unity-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/toshikiimagawa/unity-claude-code-tools/unity-build.svg)](https://agentmods.dev/skills/toshikiimagawa/unity-claude-code-tools/unity-build)
Your own site
<a href="https://agentmods.dev/skills/toshikiimagawa/unity-claude-code-tools/unity-build"><img src="https://agentmods.dev/badge/skills/toshikiimagawa/unity-claude-code-tools/unity-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 749 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 $0.00027 $0.00749
Opus 5 $0.00014 $0.00375
Sonnet 5 $0.00005 $0.00150
Haiku 4.5 $0.00003 $0.00075

Measured 3d ago against content hash ef701d44a8b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-build 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.

plugins/unity-tools-plugin/skills/unity-build/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Build

Execute Unity build validation and analyze the results. Supports batch mode (when Editor is closed) and Unity MCP (when Editor is open).

When to Use

Use this skill when:

  • User requests to build a Unity project
  • User wants to validate compilation of Unity project
  • User runs the /build command

Prerequisites

  • Unity Editor must be installed via Unity Hub
  • Current directory must be a valid Unity project (contains Assets/ folder)
  • For MCP mode: Unity MCP must be installed and running in Unity Editor

Execution Steps

Step 1: Check if Unity Editor is running

Execute the build script to check the project state:

${CLAUDE_PLUGIN_ROOT}/scripts/unity-build.sh "$(pwd)" [build-target]

The script outputs:

LOG_MODE:batch|editor

Step 2: Execute build validation based on mode

If LOG_MODE is batch (Editor is closed)

The script will run batch build automatically. Extract:

  • LOG_FILE_PATH: Path to the log file

Then call the build-result agent:

Task: build-result agent
Prompt: {log_file_path} batch
If LOG_MODE is editor (Editor is open)

Use Unity MCP to validate and test the build:

Step 2a: Validate scripts

mcp__unity-mcp__validate_script

Check for compilation errors in all scripts. This returns validation results including any syntax errors.

Step 2b: Enter Play mode (optional, for runtime validation)

mcp__unity-mcp__manage_editor with action: "play"

This enters Play mode to check for runtime errors.

Step 2c: Read console logs

mcp__unity-mcp__read_console

Read the Unity console to get compilation results, warnings, and errors.

Step 2d: Exit Play mode (if entered)

mcp__unity-mcp__manage_editor with action: "stop"

Step 2e: Report results Parse the console output and report in the standard format.

Output Format

Success:

[BUILD OK] Compilation succeeded with no errors.

With warnings:

[BUILD OK] Compilation succeeded with N warning(s).
- {FilePath}({Line},{Column}): {WarningCode} {Message}

Read the full file on GitHub · 115 lines

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 · 115 lines · 27 tokens per session scan A ef701d44a8b1

Subscribe to this mod's changes

unity-build is a skill published in the GitHub repository ToshikiImagawa/unity-claude-code-tools (2 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 749 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 2026-08-31.