Uloop Control Play Mode logo

Uloop Control Play Mode

Community
hatayama
uloop-control-play-mode

Control Unity Editor Play Mode. Use to Play (or Resume, its alias), Stop, Pause, or Step Play Mode, or query Status without side effects, for runtime behavior checks and frame inspection.

Overview

Publisherhatayama
Repositoryunity-cli-loop
Skill nameuloop-control-play-mode
Stars
578
Forks
49
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hatayama on GitHub. Read the source before you install it.

Installation

Install the Uloop Control Play Mode AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hatayama/unity-cli-loop/tree/main/.agents/skills/uloop-control-play-mode
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hatayama/unity-cli-loop.git /tmp/unity-cli-loop
mkdir -p .claude/skills
cp -r /tmp/unity-cli-loop/.agents/skills/uloop-control-play-mode .claude/skills/uloop-control-play-mode
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Uloop Control Play Mode in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Uloop Control Play Mode on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Uloop Control Play Mode is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

uloop control-play-mode

Control Unity Editor play mode (play/stop/pause/step) or query its state without side effects (status).

Usage

bash
uloop control-play-mode [options]

Parameters

ParameterTypeDefaultDescription
--actionstringPlayPlay - start Play Mode, Stop - stop Play Mode, Pause - pause Play Mode, Step - advance one frame while paused, Status - report current state without changing anything, Resume - alias of Play in every state, including starting Play Mode when stopped
--timeout-secondsinteger180Maximum seconds to wait for the requested play mode state
--unsaved-changesstringkeepHow Play from Edit Mode handles unsaved Scene/Prefab Stage changes: keep enters Play Mode without saving (like the Editor's Play button); save writes them first; fail stops if any exist

Output

Returns JSON with the current play mode state:

  • IsPlaying: Whether Unity is currently in play mode
  • IsPaused: Whether play mode is paused
  • Changed: Whether the requested action changed the current play mode state
  • WasAlreadyStopped: Whether Stop was requested while Play Mode was already stopped
  • ResumedFromPause: Whether Play resumed a paused Play Mode session instead of starting a new one
  • Message: Description of the action performed
  • Warning (string, optional): Set when the action carries a caveat. With --unsaved-changes save it starts by listing every Scene and Prefab Stage it saved. A fresh Play start always notes that the session started from Edit-time scene state; additionally, when active hot-reload patches or enabled pause points exist and Domain Reload is enabled, it reports how many of them the Play-entry domain reload will discard. Pause points enabled with --persist are counted separately: they are re-armed after the reload, and the warning points at pause-point-status for the re-arm result. Status also reports when Play Mode is running while the Unity Editor is unfocused, because progress may be throttled; run uloop focus-window, or use the pause-point --await/--trigger flow instead of polling for progress.
  • StoppedBy (string, optional): Why Play Mode last stopped: cli-control-play-mode, cli-compile-stop-setting, cli-run-tests-cancel, script-compilation, or unknown. Present on Stop when Play Mode was already stopped, and on Status when Play Mode is not running. Omitted when this Editor session has no confirmed stop.
  • StoppedAt (string, optional): UTC ISO 8601 timestamp of that stop. Omitted together with StoppedBy when no stop is recorded.
  • ActiveScenario (string, optional): Name of the active non-default Play Mode configuration (for example a Multiplayer Play Mode scenario). Omitted when the default configuration is active.

Notes

  • Stop on an already-stopped Editor sets Changed: false, WasAlreadyStopped: true
  • Play on an Editor that is already playing is a no-op: it sets Changed: false and leaves the current session (its accumulated state, spawned objects, progress) untouched instead of restarting it. If you need a clean state for verification, explicitly Stop then Play rather than relying on Play alone to reset anything.
  • Play while Play Mode is paused resumes the same session: it sets Changed: true, ResumedFromPause: true, and Message: "Play mode resumed" — the session is not restarted.
  • Resume is an alias of Play and behaves identically in every state, including starting Play Mode when stopped.
  • Step advances exactly one frame and leaves PlayMode paused (the Editor's Next Frame button); it is independent of Time.timeScale and requires PlayMode to be running
  • The command waits for the requested state before returning. Increase --timeout-seconds for projects with slow PlayMode entry.
  • Before relying on PlayMode behavior as verification evidence, check uloop get-logs --log-type Error for pre-existing errors. An error already present when PlayMode starts can otherwise be mistaken for one caused by the action under test.
  • Status reads the current state with no side effects: Changed is always false, no waiting, no scene saving, and it is never rejected by compile errors. It reports whether compile errors would currently block Play (BlockedByCompileErrors with the CompileErrors list), read from the last compile result without triggering a new compile. It does not predict unsaved-changes blocking: BlockedByUnsavedChanges describes a Play request that --unsaved-changes stopped, and Status never checks.
  • --unsaved-changes applies only when Play enters Play Mode from Edit Mode; resuming a paused session never saves or checks. With the default keep, unsaved edits stay in memory: Unity restores them when Play Mode ends, and Scene files on disk are not rewritten.
  • Play fails immediately with a CONTROL_PLAY_MODE_UNSAVED_CHANGES error when fail finds unsaved changes, or when save cannot save them — most commonly an Untitled scene, which has no path to save to. The error message lists exactly which scenes or prefab stages blocked it; use keep, or save the Untitled scene to an explicit path (or discard the changes), then retry.
  • Play and Stop follow the active Play Mode configuration like the Editor's Play button: with a Multiplayer Play Mode scenario selected they start and stop its Virtual Players too. To find and command Virtual Players, read references/multiplayer-play-mode.md.
  • Play from Edit mode triggers a domain reload (unless Enter Play Mode Options disable it), which discards all active hot-reload patches and every enabled pause point; pause points enabled with --persist are then re-armed from their saved enable request. The response Warning reports the counts being dropped and, separately, how many re-arm. Edits that were only hot-reloaded are not part of the compiled assemblies, so the new session runs the last compiled code — run uloop compile before Play to keep them, or re-apply uloop hot-reload after Play Mode starts.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Uloop Control Play Mode AI skill do?

Control Unity Editor Play Mode. Use to Play (or Resume, its alias), Stop, Pause, or Step Play Mode, or query Status without side effects, for runtime behavior checks and frame inspection.

Why use Uloop Control Play Mode on TypingMind?

Because you install it once and use it with any model. Uloop Control Play Mode is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Uloop Control Play Mode in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hatayama/unity-cli-loop/tree/main/.agents/skills/uloop-control-play-mode. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Uloop Control Play Mode?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Uloop Control Play Mode?

As many as you like. As long as a model supports skills, you can use Uloop Control Play Mode with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Uloop Control Play Mode AI skill free?

Yes. It is published on GitHub by hatayama under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇