isuzu-unity-cli

isuzu-unity-cli is a skill for Claude Code, Codex from isuzu-shiranui/UnityMCP. It costs 97 tokens per session (4,732 once invoked), scanned A, original, MIT.

A command-line tool for controlling a running Unity Editor, the application used to build games with Unity. It can run C# code, inspect scenes and objects, read console messages, capture screenshots, check compilation, control play mode, and run menu commands.

In plain words
What is it for?
Use it to inspect Unity projects and scene hierarchies, change GameObjects, run code, check compile status, manage play mode, view logs, and capture screenshots.
Why use it?
It lets an agent inspect and operate Unity directly, while using existing console errors and warnings to investigate problems.

Skill for Claude CodeCodex

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

Good fit Use it to inspect Unity projects and scene hierarchies, change GameObjects, run code, check compile status, manage play mode, view logs, and capture screenshots.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/isuzu-shiranui/unitymcp/isuzu-unity-cli
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 isuzu-shiranui/UnityMCP --skill isuzu-unity-cli
Clone the repo
git clone --depth 1 https://github.com/isuzu-shiranui/UnityMCP

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 isuzu-unity-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/isuzu-shiranui/unitymcp/isuzu-unity-cli.svg)](https://agentmods.dev/skills/isuzu-shiranui/unitymcp/isuzu-unity-cli)
Your own site
<a href="https://agentmods.dev/skills/isuzu-shiranui/unitymcp/isuzu-unity-cli"><img src="https://agentmods.dev/badge/skills/isuzu-shiranui/unitymcp/isuzu-unity-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 137
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00097 $0.04732
Opus 5 $0.00048 $0.02366
Sonnet 5 $0.00019 $0.00946
Haiku 4.5 $0.00010 $0.00473

Measured 2d ago against content hash 1188383345c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

isuzu-unity-cli 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.

isuzu-unity-cli/skills/isuzu-unity-cli/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity MCP - CLI Control for Unity Editor

Drive a running Unity Editor with the isuzu-unity-cli command. It reads the descriptor file the Editor publishes, so it needs no port scan, no token handling, and no MCP client running.

isuzu-unity-cli projects   # which Editors are running
isuzu-unity-cli tools      # what this Editor publishes, with argument names
isuzu-unity-cli health     # server state, queue depth, running jobs

Read the console first

When something does not work or does not show up, read the console errors and warnings before building any instrumentation of your own (reflection reads, debug counters, synthetic tests).

isuzu-unity-cli call console_read_logs --type error --limit 30

Unity has usually already written down the cause in one line. Order diagnostics by cost: console, then existing debug displays, then your own instrumentation.

  • Check both --type error and --type warning as soon as a symptom appears. The cause is sometimes on the warning side.
  • Do not trust an empty console. If entries may have been dropped, read the log file directly with editor_log_tail. It works while the Editor is busy.
  • After a compile, reimport or recompile, confirm succeeded with compile_status. A failed compile leaves the Editor running the previous assembly with isCompiling back to false, so silence is not success.
  • "Fix until the errors are gone" is itself an objective completion criterion.

Calling tools

isuzu-unity-cli call <tool>                                # no arguments
isuzu-unity-cli call <tool> --name value --other 3         # individual arguments
isuzu-unity-cli call <tool> --json '{"key":"value"}'       # one JSON object
isuzu-unity-cli call <tool> --project MyGame               # when several Editors are open
isuzu-unity-cli call <tool> --raw                          # whole envelope, not just the result

Values are typed automatically. --limit 20 sends a number and --active_only true sends a boolean. Errors print to stderr and set a non-zero exit code, so the commands can be used in scripts.

Read the full file on GitHub · 378 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. 2d ago Changed · +50 lines 1188383345c2
  2. 3d ago First seen · 328 lines · 97 tokens per session scan A 33e094c8c6ca

Subscribe to this mod's changes

isuzu-unity-cli is a skill published in the GitHub repository isuzu-shiranui/UnityMCP (140 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 4,732 once invoked, about $0.0005 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 2026-09-05.