Borrowing it
Nothing to install: this file belongs to ReactUnity/core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ReactUnity/core/main/.claude/skills/unity/SKILL.mdgit clone --depth 1 https://github.com/ReactUnity/coreWrote 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/reactunity/core/unity)<a href="https://agentmods.dev/skills/reactunity/core/unity"><img src="https://agentmods.dev/badge/skills/reactunity/core/unity/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.
<a href="https://agentmods.dev/skills/reactunity/core/unity"><img src="https://agentmods.dev/badge/skills/reactunity/core/unity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 71 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00108 | $0.05609 |
| Opus 5.5 | $0.00043 | $0.02244 |
| Sonnet 5.5 | $0.00022 | $0.01122 |
| Haiku 4.5 | $0.00011 | $0.00561 |
Grade A, and why
unity 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 1mo 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving Unity from here
Two ways in, and they are two different tools. Pick by whether an Editor is already open on the project.
pnpm unity <cmd> (batch mode) |
unity <cmd> (open Editor) |
|
|---|---|---|
| Is | this repo's driver, scripts/unity/ | Unity's own CLI, installed on this machine |
| Needs | the project not open in an Editor | the project open, with com.unity.pipeline (both have it) |
| Speed | ~8 s compile, ~70 s EditMode suite | 200–600 ms per command, no recompile, no domain reload |
| Use for | compile, the suites, IL2CPP players — anything scriptable, and the only CI-faithful results | an Editor the user already has open, play mode, screenshots, scene and asset edits |
The second one is not mainly a speed win — it is how you work without closing someone's Editor, and the only way to reach play mode and screenshots. See Unity's own CLI for what it can do and where it must not be used.
This repo used to carry its own version of that: an AgentBridge loopback server plus a pnpm unity bridge client. Both are gone — the Pipeline package does all of it and more. A pnpm unity bridge … invocation found anywhere is stale; the table below says what it became.
The two refuse to fight each other: batch mode checks the project lock first and points at the other tool.
The loop for a C# change
pnpm unity compile tests
8 seconds warm, and it reports file(line,col): CSxxxx: message for every error. Run this after every C# edit under unity/** — it is far cheaper than the test suite and catches the majority of mistakes. Nothing else in this repo type-checks C#; pnpm typecheck is TypeScript only.
Then the suites:
pnpm unity test tests
EditMode then PlayMode (two Unity invocations — -testPlatform All is a game-ci concept that Unity rejects with exit code 4). Narrow it while iterating:
pnpm unity test tests --platform EditMode --filter ReactUnity.Tests.StyleTests
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.
- 1mo ago Changed · +2 lines 9aa28a8940b0
- 1mo ago Changed · +16 lines 9bedaab1ebb2
- 1mo ago Changed 80d1378000c0
- 1mo ago Changed · +2 lines a3dd7c911abb
- 2mo ago First seen · 198 lines · 108 tokens per session scan A e5ea586b544c
unity is a skill published in the GitHub repository ReactUnity/core (904 stars, last pushed 4d ago), licensed MIT. It adds 108 tokens to every session and 5,609 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 2026-08-30.
unity compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unityReactUnity/core | Skill | 904 | 4d ago | MIT | A | 108 | Claude Code |
| asp-ft-player-buildsVPDPersonal/Aspid.FastTools | Skill | 24 | yesterday | MIT | A | 99 | Claude Code |
| test-designing-guidenowsprinting/unity-coding-skills | Skill | 20 | 8d ago | Unlicense | A | 52 | Claude Code |
| test-writing-guidenowsprinting/unity-coding-skills | Skill | 20 | 8d ago | Unlicense | A | 81 | Claude Code |
| run-testsnowsprinting/unity-coding-skills | Skill | 20 | 8d ago | Unlicense | A | 130 | Claude Code |
| unity-uibigdra50/unity-cli | Skill | 39 | 4mo ago | MIT | A | 81 | Claude Code |
| unity-verifybigdra50/unity-cli | Skill | 39 | 4mo ago | MIT | A | 60 | Claude Code |