unity-cli-loop: Skill for Claude Code

.agents/skills/uloop-record-video/SKILL.md

uloop-record-video is a skill for Claude Code, Codex from hatayama/unity-cli-loop. It costs 107 tokens per session (1,729 once invoked), scanned A, original, MIT.

A Unity tool that records the Game View during Play Mode as an MP4 or WebM video. Unity is a game engine, and Play Mode runs the game inside the editor.

In plain words
What is it for?
It is for recording and later reviewing Unity gameplay or editor simulations, with optional frame extraction for inspection.
Why use it?
A video captures movement, animation, transitions, physics, and gameplay sequences that a still screenshot cannot show.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is hatayama/unity-cli-loop's own configuration. It tells Claude Code and Codex how to work on unity-cli-loop itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unity-cli-loop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hatayama/unity-cli-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hatayama/unity-cli-loop/main/.agents/skills/uloop-record-video/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hatayama/unity-cli-loop

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 uloop-record-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/hatayama/unity-cli-loop/uloop-record-video/github.svg)](https://agentmods.dev/skills/hatayama/unity-cli-loop/uloop-record-video)
Your own site
<a href="https://agentmods.dev/skills/hatayama/unity-cli-loop/uloop-record-video"><img src="https://agentmods.dev/badge/skills/hatayama/unity-cli-loop/uloop-record-video/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 uloop-record-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/hatayama/unity-cli-loop/uloop-record-video"><img src="https://agentmods.dev/badge/skills/hatayama/unity-cli-loop/uloop-record-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,729 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.
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 $0.00107 $0.01729
Opus 5.5 $0.00043 $0.00692
Sonnet 5.5 $0.00021 $0.00346
Haiku 4.5 $0.00011 $0.00173

Measured 7d ago against content hash 4d51b3026dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uloop-record-video 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 7d 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.

.agents/skills/uloop-record-video/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

Record the Game View during Play Mode, or any Editor window with --window-name, and read what happened from PNG sheets and numbers instead of the video.

Workflow

  1. A Game View recording needs Play Mode (uloop control-play-mode --action Play); --window-name does not.
  2. uloop record-video --seconds 3 --trigger "simulate-keyboard --action Press --key Space" (the trigger is a uloop command without the leading uloop): focuses Unity, starts, runs the trigger, marks the moment it returns, waits, stops, and prints one JSON.
  3. Read the PNG at BurstSheetPath: up to 32 consecutive frames, 4 columns, top-left first. BurstFrames gives each tile's EncodedFrame and Seconds; BurstAnchor: "mark" centers it on the trigger, "largest-change" on the biggest change.
  4. Read the PNG at TimelineSheetPath: the whole recording at even spacing, 5 columns.
  5. Read FrameChange (below).
  6. To look closer, with ffmpeg installed (works with Unity closed): uloop record-video --video <OutputPath> --sheet-from <s> --sheet-to <s>, or --frame-at <s> for one full-size frame. Pass the Seconds the sheets report.

Choosing the trigger

  • Input: simulate-keyboard, simulate-mouse-input, simulate-mouse-ui, replay-input.
  • Code reaching a line (an AI branch, a coroutine stage): enable-pause-point --file <f> --line <n> --mode trace --await. Trace does not pause Play Mode; other modes are rejected. For long waits raise --seconds and --max-duration-seconds.

Reading the numbers

  • FramesChangedVsPrevious counts frames where 2+ grid cells (1/64 of the width) changed by CellChangedThreshold or more. Smaller areas do not register; look at the burst sheet.
  • Judge flicker by FramesChangedVsPreviousMatchingTwoBack and TopAlternatingCells[].Count (rectangles in video pixels, top-left origin), not FramesChangedVsPrevious alone: smooth motion keeps that high after a fix. Measured (FramesChangedVsPrevious / MatchingTwoBack / Count): a one-frame blink 62 / 30 / 30; the same element fixed to a 1 s pulse 58 / 3 / 4.

Read the full file on GitHub · 74 lines

Files

What ships with it

1 file 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. 7d ago Changed · -8 lines · +58 tokens per session 4d51b3026dc6
  2. 28d ago Changed · -38 tokens per session b8b36d306024
  3. 1mo ago Changed e486763f3bd6
  4. 1mo ago Changed · +4 lines · +11 tokens per session f968f81623f1
  5. 1mo ago First seen · 78 lines · 76 tokens per session scan A 899cf36ab828

Subscribe to this mod's changes

uloop-record-video is a skill published in the GitHub repository hatayama/unity-cli-loop (586 stars, last pushed 2d ago), licensed MIT. It adds 107 tokens to every session and 1,729 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-07.