UnitySkills is a REST API-based automation engine that lets AI coding agents control Unity Editor projects, including scenes and other editor operations. It is for developers using Unity with supported coding agents and IDEs. The catalogue skills and commands provide the agent workflows used to operate Unity projects through the engine.
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/besty0728/unity-skills/cleanernpx skills add Besty0728/Unity-Skills --skill cleanergit clone --depth 1 https://github.com/Besty0728/Unity-SkillsWrote 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.
[](https://agentmods.dev/skills/besty0728/unity-skills/cleaner)<a href="https://agentmods.dev/skills/besty0728/unity-skills/cleaner"><img src="https://agentmods.dev/badge/skills/besty0728/unity-skills/cleaner.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.02666 |
| Opus 5 | $0.00005 | $0.01333 |
| Sonnet 5 | $0.00002 | $0.00533 |
| Haiku 4.5 | $0.00001 | $0.00267 |
Grade A, and why
unity-cleaner 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before calling any skill in this module: if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via
GET /skills/recommend?includeSchema=true) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun.
Triggers
- Reducing project bloat
- Hunting duplicate or orphaned assets
- Auditing before a release
- 给项目瘦身、排查重复或孤立资源、发布前审计
Unity Cleaner Skills
Safety:
cleaner_delete_assetsuses a two-step confirmToken handshake. Call withoutconfirmTokento preview; call again with the returned token (5-minute TTL) to actually delete. There is nodryRunparameter.
Guardrails
Operating Mode (v1.9 three-tier):
- Approval (default): all analyze/query skills (
cleaner_find_unused_assets,cleaner_find_duplicates,cleaner_find_missing_references,cleaner_get_asset_usage,cleaner_find_empty_folders,cleaner_find_large_assets,cleaner_get_dependency_tree) are SemiAuto — run directly. - Auto / Bypass: SemiAuto and FullAuto run directly.
- Auto-forbidden in this module:
cleaner_delete_assets,cleaner_delete_empty_folders(both carrySkillOperation.Delete). In Approval/Auto these returnMODE_FORBIDDEN— they are reachable only under Bypass mode or via a user-managed Allowlist entry; the grant flow does not unlock them. cleaner_fix_missing_scriptsis anExecute | Modifyoperation (it replaces missing component references with null in place, no asset deletion), so it does not trigger the NeverInSemi gate. In Auto / Bypass it runs directly; in Approval it still requires the standard grant handshake before execution.cleaner_delete_assetsadditionally uses a two-stepconfirmTokenhandshake even when the mode gate allows it — preview first (no token), then confirm with the returned token (5-minute TTL).
DO NOT (common hallucinations):
cleaner_delete/cleaner_removedo not exist → cleaner skills only find/report; useasset_deleteto actually removecleaner_fixdoes not exist → usecleaner_fix_missing_scriptsspecifically for missing script referencescleaner_scan/cleaner_find_unuseddo not exist → use specific skills:cleaner_find_unused_assets,cleaner_find_duplicates,cleaner_find_missing_references,cleaner_find_empty_folders,cleaner_find_large_assets
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.
- 5d ago First seen · 272 lines · 11 tokens per session scan A 9e2c1e127dc5
unity-cleaner is a skill published in the GitHub repository Besty0728/Unity-Skills (1,707 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 2,666 once invoked, about $0.0001 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
2dimg2motion
Use when a user provides one baseline image and requests game animation frames, sprite sequences, attack/walk/idle/hit/death/casting motion, transparent PNG frames, a spritesheet, keyframe prompts, or consistent whole-character pose animation.
dotcraft-unity
Use when dotcraft-unity MCP, CLI, or unityexecutecsharp is available, or when the user asks to inspect, automate, capture, or debug Unity Editor state, scenes, assets, Console logs, or GameView output. Provides background-first Unity Editor automation through MCP or CLI.
img2mo-learn
Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…
zu-article-image-skill
为已完成的 Markdown 文章设计语义配图位置，按内置 preset/type/style/palette 样式体系生成可编辑自然语言生图 Prompt，并作为隐藏标签插入文章；用户确认后扫描标签，调用当前运行时原生 imagegen 生成图片并插回文章。用于用户要求为文章配图、规划正文插图、调整文章插图风格或根据文章内 Prompt 标签生成图片时。.
msh-exam-analysis
名师汇出国自动化工具集。两个功能：(1) 模考错题分析——用户提供 mingshihuichuguo.com/homework/student/ 网址，按"手写版"人味风格产出阅读/听力错题分析 txt；(2) 单词听写自动化——用户要求完成 list 听写/单词测试时，用 playwright-cli + runv5.js 自动答题。根据用户意图自动判断用哪个。When the user mentions 错题分析 / 模考 / 听写 / 单词 / list / mingshihuichuguo URL, use this skill.
newbie-guide
中文新手引导。当用户有模糊目标、不会拆任务、不知道如何开始时使用。由 workflow-system 或其他子技能调用。.