Install the "script-execute" agent skill from https://github.com/IvanMurzak/Unity-MCP/tree/main/Unity-MCP-Plugin/.claude/skills/script-execute into .claude/skills/script-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "script-execute", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add IvanMurzak/Unity-MCP --skill script-execute -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "script-execute" agent skill from https://github.com/IvanMurzak/Unity-MCP/tree/main/Unity-MCP-Plugin/.claude/skills/script-execute into .agents/skills/script-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "script-execute", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add IvanMurzak/Unity-MCP --skill script-execute -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "script-execute" agent skill from https://github.com/IvanMurzak/Unity-MCP/tree/main/Unity-MCP-Plugin/.claude/skills/script-execute into .cursor/skills/script-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "script-execute", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add IvanMurzak/Unity-MCP --skill script-execute -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "script-execute" agent skill from https://github.com/IvanMurzak/Unity-MCP/tree/main/Unity-MCP-Plugin/.claude/skills/script-execute into .gemini/skills/script-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "script-execute", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add IvanMurzak/Unity-MCP --skill script-execute -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "script-execute" agent skill from https://github.com/IvanMurzak/Unity-MCP/tree/main/Unity-MCP-Plugin/.claude/skills/script-execute into .github/skills/script-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "script-execute", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add IvanMurzak/Unity-MCP --skill script-execute -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "script-execute" agent skill from https://github.com/IvanMurzak/Unity-MCP/tree/main/Unity-MCP-Plugin/.claude/skills/script-execute into .opencode/skills/script-execute/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "script-execute", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
script-execute
GitHub stars
4.4k
Token cost
~2k tokens
SKILL.md length
473 words
Files
1
Skills in repo
80
Repo updated
First seen
Licence
Apache-2.0
At a glance
Compiles and executes C code dynamically using Roslyn. An agent skill from IvanMurzak/Unity-MCP.
Tasks that involve Game development
SKILL.md covers Modes, Passing Unity objects as…, How to Call and Input, plus 1 more section
Calls npm and npx
What it does
Script Execute is an agent skill from IvanMurzak/Unity-MCP. Compiles and executes C code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Game Development, covering Game development. It works with C# and Model Context Protocol. The repository describes itself as: AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C method may be turned into a… The licence is Apache-2.0.
When your agent uses it
Tasks that involve Game development
Example prompts
“Use the script-execute skill to compile and executes C code dynamically using Roslyn. An agent skill from IvanMurzak/Unity-MCP”
“/script-execute”
Requirements
Node.js
What it can do on your machine
Read from SKILL.md and the folder at commit 4c8056f. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npm
npx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm and npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Script Execute loads about 2k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 473 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~57
When it runs· the whole SKILL.md, loaded when a task matches
~2k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/script-execute/SKILL.md (or your agent's skills folder).
name
script-execute
description
Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.
Script / Execute
Modes
Full code mode (default, isMethodBody=false): the csharpCode argument must define a complete class with a static method (no top-level statements).
Body-only mode (isMethodBody=true): provide only the method body statements. The tool auto-generates the usings, class, and method header.
Passing Unity objects as parameters
Unity objects (GameObject, Component, etc.) can be passed as parameters using their Ref types (GameObjectRef, ComponentRef, etc.) or directly by type:
UnityEngine.GameObject — resolves an actual GameObject from value {"instanceID": N}, {"name": "..."}, or {"path": "..."}.
UnityEngine.Component (or any component subtype) — resolves from {"instanceID": N}.
AIGD.GameObjectRef — passes a GameObjectRef POCO directly; the method body calls goRef.FindGameObject() to resolve it.
If unity-mcp-cli is not found, either install it globally (npm install -g unity-mcp-cli) or use npx unity-mcp-cli instead.
Read the /unity-initial-setup skill for detailed installation instructions.
Input
Name
Type
Required
Description
csharpCode
string
Yes
C# code to compile and execute. In full code mode (default, isMethodBody=false): must define a complete class with a static method. Example: 'using UnityEngine; public class Script { public static void Main() { Debug.Log("Hello"); } }'. Do NOT use top-level statements. In body-only mode (isMethodBody=true): provide only the method body statements. The tool auto-generates usings, class, and method header. Example body: 'go.SetActive(false);'. Custom helper classes can still be defined inline in the body-only string after the main logic, but for complex additional class definitions use full code mode instead.
className
string
No
The name of the class containing the method to execute. In body-only mode this becomes the generated class name.
methodName
string
No
The name of the method to execute. Must be a static method. In body-only mode this becomes the generated method name.
parameters
any
No
Serialized parameters to pass to the method. Each entry must specify 'name' and 'typeName'. Supported parameter types include primitives, strings, and Unity object references: - 'UnityEngine.GameObject': resolves an actual GameObject from value '{"instanceID": N}', '{"name": "..."}', or '{"path": "..."}'. - 'UnityEngine.Component' (or any component subtype): resolves from '{"instanceID": N}'. - 'AIGD.GameObjectRef': passes a GameObjectRef POCO directly; the method body calls goRef.FindGameObject() to resolve it. - 'AIGD.ComponentRef': passes a ComponentRef POCO. - 'AIGD.ObjectRef': passes a base ObjectRef POCO. If the method does not require parameters, leave this empty.
isMethodBody
boolean
No
When true, 'csharpCode' is treated as just the method body. The tool auto-generates standard using directives (System, UnityEngine, AIGD, com.IvanMurzak.Unity.MCP.Runtime.Extensions, UnityEditor), the class definition, and the method signature (void return type). Parameters from the 'parameters' list are automatically added to the method signature using their typeName and name. When false (default), 'csharpCode' must be a complete C# compilation unit with class and method definitions.
Show full SKILL.md (7 more words)Show less
Input JSON Schema
json
{
"type": "object",
"properties": {
"csharpCode": {
"type": "string"
},
"className": {
"type": "string"
},
"methodName": {
"type": "string"
},
"parameters": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMemberList"
},
"isMethodBody": {
"type": "boolean"
}
},
"$defs": {
"com.IvanMurzak.ReflectorNet.Model.SerializedMemberList": {
"type": "array",
"items": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember"
}
},
"com.IvanMurzak.ReflectorNet.Model.SerializedMember": {
"type": "object",
"properties": {
"typeName": {
"type": "string",
"description": "Full type name. Eg: 'System.String', 'System.Int32', 'UnityEngine.Vector3', etc."
},
"name": {
"type": "string",
"description": "Object name."
},
"value": {
"description": "Value of the object, serialized as a non stringified JSON element. Can be null if the value is not set. Can be default value if the value is an empty object or array json."
},
"fields": {
"type": "array",
"items": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember",
"description": "Nested field value."
},
"description": "Fields of the object, serialized as a list of 'SerializedMember'."
},
"props": {
"type": "array",
"items": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember",
"description": "Nested property value."
},
"description": "Properties of the object, serialized as a list of 'SerializedMember'."
}
},
"required": [
"typeName"
],
"additionalProperties": false
}
},
"required": [
"csharpCode"
]
}
Output
Output JSON Schema
json
{
"type": "object",
"properties": {
"result": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember"
}
},
"$defs": {
"com.IvanMurzak.ReflectorNet.Model.SerializedMemberList": {
"type": "array",
"items": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember"
}
},
"com.IvanMurzak.ReflectorNet.Model.SerializedMember": {
"type": "object",
"properties": {
"typeName": {
"type": "string",
"description": "Full type name. Eg: 'System.String', 'System.Int32', 'UnityEngine.Vector3', etc."
},
"name": {
"type": "string",
"description": "Object name."
},
"value": {
"description": "Value of the object, serialized as a non stringified JSON element. Can be null if the value is not set. Can be default value if the value is an empty object or array json."
},
"fields": {
"type": "array",
"items": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember",
"description": "Nested field value."
},
"description": "Fields of the object, serialized as a list of 'SerializedMember'."
},
"props": {
"type": "array",
"items": {
"$ref": "#/$defs/com.IvanMurzak.ReflectorNet.Model.SerializedMember",
"description": "Nested property value."
},
"description": "Properties of the object, serialized as a list of 'SerializedMember'."
}
},
"required": [
"typeName"
],
"additionalProperties": false
}
},
"required": [
"result"
]
}
Script Execute next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
A skill your agent uses when an agent needs to inspect or control a real Unity Editor through Locus, especially when Unity MCP is unavailable, named-pipe discovery is needed, C must be executed, or…
Compiles and executes C code dynamically using Roslyn. An agent skill from IvanMurzak/Unity-MCP. Script Execute is an agent skill from IvanMurzak/Unity-MCP. Compiles and executes C code dynamically using Roslyn.
When should I use Script Execute?
Script Execute fits situations like: tasks that involve Game development.
How do I install Script Execute in Claude Code?
Run `npx skills add IvanMurzak/Unity-MCP --skill script-execute -a claude-code`. Or copy the skill folder (Unity-MCP-Plugin/.claude/skills/script-execute in IvanMurzak/Unity-MCP) into .claude/skills/script-execute in your project. Claude Code loads it when a task matches its description.
How do I install Script Execute in Codex?
Run `npx skills add IvanMurzak/Unity-MCP --skill script-execute -a codex`. Or copy the skill folder (Unity-MCP-Plugin/.claude/skills/script-execute in IvanMurzak/Unity-MCP) into .agents/skills/script-execute in your project. Codex loads it when a task matches its description.
Can I use Script Execute in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add IvanMurzak/Unity-MCP --skill script-execute -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/script-execute, .gemini/skills/script-execute, .github/skills/script-execute and .opencode/skills/script-execute in your project.
What does Script Execute need to run?
Going by SKILL.md and its folder, Script Execute needs the command-line tools its instructions call (npm and npx). Our summary lists: Node.js.
Does Script Execute access the network?
SKILL.md contains no URLs. Its commands use npm and npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Script Execute safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Script Execute use?
Script Execute is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Script Execute use?
About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Script Execute?
Skills that share tags, products or a category with Script Execute: Unity Plugin (TomLeeLive/openclaw-unity-plugin, 107 stars), Sprite Gen (aldegad/sprite-gen, 2.6k stars), Unreal Blueprint Authoring (flopperam/unreal-engine-mcp, 1.1k stars) and Locus Unity Bridge (Misaka-Mikoto-Tech/agent-skills, 275 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Script Execute?
IvanMurzak (a GitHub user) maintains it in IvanMurzak/Unity-MCP, which has 4,398 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on October 4, 2026.
Source: IvanMurzak/Unity-MCP on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
