unity-pipeline-commands

unity-pipeline-commands is a skill for Claude Code, Codex from menstood/unity-pipeline-commands-skill. It costs 90 tokens per session (2,653 once invoked), scanned B, original, MIT.

A command interface for controlling a running Unity Editor or development game build through a local connection. It can make project changes and run Editor actions without requiring a person to click through the interface.

In plain words
What is it for?
Use it to edit Unity scenes, assets, and prefabs; enter play mode; take screenshots; read logs; recompile; run tests; build; and execute C# code.
Why use it?
It automates repetitive Unity work and makes compiling, testing, logging, screenshots, and asset or scene changes usable from scripts or an assistant.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to edit Unity scenes, assets, and prefabs; enter play mode; take screenshots; read logs; recompile; run tests; build; and execute C# code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands
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.

Any agent
npx skills add menstood/unity-pipeline-commands-skill --skill unity-pipeline-commands
Clone the repo
git clone --depth 1 https://github.com/menstood/unity-pipeline-commands-skill

Made for: Claude Code, Codex.

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-pipeline-commands

README.md
[![agentmods](https://agentmods.dev/badge/skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands/github.svg)](https://agentmods.dev/skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands)
Your own site
<a href="https://agentmods.dev/skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands"><img src="https://agentmods.dev/badge/skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unity-pipeline-commands

Your own site · 80×15
<a href="https://agentmods.dev/skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands"><img src="https://agentmods.dev/badge/skills/menstood/unity-pipeline-commands-skill/unity-pipeline-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,653 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00090 $0.02653
Opus 5.5 $0.00036 $0.01061
Sonnet 5.5 $0.00018 $0.00531
Haiku 4.5 $0.00009 $0.00265

Measured 2d ago against content hash fc93937bec41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

unity-pipeline-commands scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

unity command <name> [--arg value ...] # run any command, e.g.:
skills/unity-pipeline-commands/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Pipeline Commands (com.unity.pipeline) — drive the Unity Editor over HTTP

The com.unity.pipeline package (v0.3.x, experimental) runs a local HTTP server inside the Unity Editor (and optionally inside development Player builds). Clients — the unity CLI, CI, or this agent — execute registered commands against it. This is how you can actually compile, test, screenshot, and edit scenes without a human in the Editor.

Prerequisite: package installed?

Check Packages/manifest.json for "com.unity.pipeline". If missing, report it and ask before installing — installing edits the manifest and triggers a domain reload. (Options once approved: unity pipeline install with the CLI, or Package Manager → Install package by name → com.unity.pipeline, version blank = latest.) The Editor must be running with the project open for the server to exist.

Connecting (do this first, every session)

  1. Read the port descriptor the Editor writes:
    • Editor: <projectPath>/Library/Pipeline/.unity-pipeline-port
    • Player: <workingDirectory>/.unity-pipeline-runtime-port
  2. It's JSON — extract port and evalToken (also has pid, projectName, unityVersion, mode, lastHeartbeat).
  3. Call http://127.0.0.1:<port>/... with header Authorization: Bearer <evalToken>. Always use 127.0.0.1, not localhost (IPv6 pitfalls). Missing/wrong token → 401.

Ports: Editor 7800–7849 (tests 7850–7899), Runtime 7900–7949 (tests 7950–7999). Token is 256-bit CSPRNG, base64, regenerated after every domain reload — re-read the descriptor after any recompile/package change.

Treat evalToken as a secret: never print, log, or commit it (descriptors live under Library/, which Unity projects git-ignore); read it only to build the auth header and re-read after reloads instead of storing it.

Project identity check (before any mutation)

A reachable server + valid token does NOT prove you're talking to the right project. Before the first mutating command:

Read the full file on GitHub · 133 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 133 lines · 90 tokens per session scan B fc93937bec41

Subscribe to this mod's changes

unity-pipeline-commands is a skill published in the GitHub repository menstood/unity-pipeline-commands-skill (19 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 2,653 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.

Related

unity-pipeline-commands compared with skills from other repositories

unity-pipeline-commands next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
unity-pipeline-commandsmenstood/unity-pipeline-commands-skillSkill193d agoMITB90Claude Code, Codex
playtest-reportDonchitos/Claude-Code-Game-StudiosSkill36k19d agoMITA20Claude Code
godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skillsSkill6.9k9d agoApache-2.0A95Claude Code
scenario-unreal-gameplayscenario-labs/skillsSkill3.2kyesterdayMITA121Claude Code
motionOpenDCAI/GameFactory-3ASkill1.0k8d agoApache-2.0A0Claude Code, Codex
unity-addressablesBesty0728/Unity-SkillsSkill1.9kyesterdayMITA25Claude Code, Codex
unity-manual-componentBesty0728/Unity-SkillsSkill1.9kyesterdayMITA36Claude Code, Codex