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.
npx agentmods add skills/hatayama/unity-cli-loop/uloop-replay-inputnpx skills add hatayama/unity-cli-loop --skill uloop-replay-inputgit clone --depth 1 https://github.com/hatayama/unity-cli-loopWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.00566 |
| Opus 5 | $0.00016 | $0.00283 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
uloop-replay-input 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uloop replay-input
Replay recorded keyboard and mouse input during PlayMode. Loads a JSON recording and injects input frame-by-frame via Input System with zero CLI overhead. Supports looping and progress monitoring.
Create recording JSON files in the Unity Editor from Window > Unity CLI Loop > Recordings with Start Recording and Stop Recording. There is no CLI command for recording input.
Usage
# Start replay (auto-detect latest recording)
uloop replay-input --action Start
# Start replay with specific file
uloop replay-input --action Start --input-path scripts/my-play.json
# Start replay with looping
uloop replay-input --action Start --loop
# Check replay progress
uloop replay-input --action Status
# Stop replay
uloop replay-input --action Stop
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
--action |
enum | Start |
Start - begin replaying, Stop - stop mid-way, Status - check progress |
--input-path |
string | auto | Path to the recording JSON. When empty, auto-detects the latest recording in .uloop/outputs/InputRecordings/ |
--no-show-overlay |
flag | - | Hide replay progress overlay |
--loop |
flag | - | Loop continuously |
Deterministic Replay
Replay injects the exact same input frame-by-frame, but the game must also be deterministic to produce identical results. If replay output must be compared across runs, read references/deterministic-replay.md before interpreting failures.
Prerequisites
- Unity must be in PlayMode
- Input System package (
com.unity.inputsystem) must be installed; this tool only works with the New Input System.
Output
Returns JSON with:
Success: Whether the operation succeededMessage: Status messageAction: Echoes which action was executed (Start,Stop, orStatus)InputPath: Path to recording file (nullable string; populated onStartonly)CurrentFrame: Current replay frame index (nullable int)TotalFrames: Total frames in the recording (nullable int)Progress: Replay progress (nullable float in 0.0 – 1.0)IsReplaying: Whether replay is currently active (nullable bool)
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.
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.
- yesterday Changed · +1 lines 05d83e0a80a1
- 2d ago First seen · 61 lines · 33 tokens per session scan A 7e8f1f4b3e45
uloop-replay-input is a skill published in the GitHub repository hatayama/unity-cli-loop (522 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 566 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
unity
Compile, test, and drive Unity for this repo's C# packages (unity/core, jint, quickjs, clearscript) and the two Unity projects (tests/, kitchen-sink/). Use when a change touches C# under unity/, when Unity test results are needed, when a rendering snapshot has to be checked or regenerated, or when the app has to be…
test-designing-guide
Provides test design methodology for Unity projects. Use this skill whenever designing test cases from requirements or specifications, including selecting test techniques, deriving test cases, and formatting them. Even for small features, load this skill to ensure test design rigor.
fix-bug
Diagnoses and fixes bugs using a test-first workflow (reproduce, diagnose, fix). Use this skill whenever the user reports a bug, describes unexpected behavior, or asks to investigate or fix a defect. Even if the user says "something's broken", "this isn't working", "fix this bug", or "why does X happen", load this…
test-writing-guide
Provides guidelines for writing test code for Unity projects. Make sure to use this skill whenever writing, creating, editing, or modifying test code files (files under Tests/). This includes implementing new tests, fixing test failures, adding test cases, or any task that results in test code changes. Even for small…
plan-feature
Orchestrates the test-first implementation planning workflow for feature implementation and spec changes. Use this skill whenever plan mode is active and the task involves implementing or adding a new feature, or changing an existing specification. Even if the user only says "plan this" or "how should we implement…
refine-tests
Reviews existing test code for conformance to the test-designing-guide and test-writing-guide, then applies the refinements. Use this skill when the user wants to review or refine existing test code so it follows the project's test design and writing conventions. Typically invoked as /refine-tests .