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 skills add Besty0728/Unity-Skills --skill workflowgit 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/workflow)<a href="https://agentmods.dev/skills/besty0728/unity-skills/workflow"><img src="https://agentmods.dev/badge/skills/besty0728/unity-skills/workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Rogue Agent · line 311 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 5.1 | $0.00010 | $0.03911 |
| Opus 5 | $0.00005 | $0.01956 |
| Sonnet 5 | $0.00002 | $0.00782 |
| Haiku 4.5 | $0.00001 | $0.00391 |
Grade A, and why
unity-workflow 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 4d 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 — 353 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
- Undoing a whole task or session
- Snapshotting before risky changes
- Planning/previewing batch operations
- Rolling back
- 撤销整个任务或会话、高危改动前快照、规划/预览批量操作、回滚
Workflow Skills
Persistent history and rollback system for AI operations ("Time Machine"). Allows tagging tasks, snapshotting objects before modification, and undoing specific tasks even after Editor restarts.
NEW: Session-level undo - Group all changes from a conversation and undo them together.
Operating Mode
- Approval：本模块大部分 skill 标
SkillMode.SemiAuto（bookmark / history / task / session 系列里的纯读查询 +workflow_plan，后者 ReadOnly=true 仅生成聚合计划），可直接执行。有副作用的 skill (bookmark_set/bookmark_goto/workflow_snapshot_object/workflow_snapshot_created/batch_retry_failed) 走默认SkillMode.FullAuto，需 grant。 - Auto / Bypass：FullAuto 直接执行。
- 含 NeverInSemi 高危 skill：
bookmark_delete/workflow_delete_task（标 Operation.Delete，删除书签/任务记录）、workflow_clear_history（Operation.Delete + RiskLevel=high，清空全部历史+redo栈+文件存储，不可逆）。这些在 Approval/Auto 下返MODE_FORBIDDEN，仅 Bypass 或 Allowlist 命中可调。
注意：
workflow_undo_task/workflow_session_undo不是 Delete operation（标的是 Modify/Execute），它们能在 Approval/Auto 直接撤销已记录任务。
Surface profile: workflow_undo_task / workflow_redo_task / workflow_revert_task / workflow_session_undo inspect every snapshot the target task(s) would restore. If any snapshot would author a category the active profile withdraws — a scene GameObject, or a .unity / .mat asset — the whole call is refused with SURFACE_EXCLUDED (surfaceProfile/category/operation/manualDoc/userControlled/hint at the top level, not nested under details) rather than partially applied. Snapshots of scripts, prefabs, textures, ScriptableObjects, and Editor/project settings are unaffected — those stay undoable under every profile.
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.
- 4d ago First seen · 353 lines · 10 tokens per session scan A 1a0f4b953ae0
unity-workflow is a skill published in the GitHub repository Besty0728/Unity-Skills (1,714 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 3,911 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 2026-09-03.
Other skills, from other repositories
phase-closeout
A Chinese-language stage closer that summarizes completed work, records decisions, updates project status, and prepares the next conversation.
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
help-center-article-generator
Take support ticket clusters, FAQ patterns, product documentation, or feature specs and generate structured help center articles with step-by-step instructions, screenshot placeholders, troubleshooting sections, and related article links. Batch mode generates multiple articles from a ticket export. Pure reasoning…
contact-cache
Track all identified/contacted people across strategies. CSV-backed contact database with dedup by LinkedIn URL or email. Prevents duplicate outreach when running strategies on a recurring cadence.
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
summarize
Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.