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.
git clone --depth 1 https://github.com/NotNull92/hera-agent-unityWrote 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/rules/notnull92/hera-agent-unity/cursor)<a href="https://agentmods.dev/rules/notnull92/hera-agent-unity/cursor"><img src="https://agentmods.dev/badge/rules/notnull92/hera-agent-unity/cursor/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/rules/notnull92/hera-agent-unity/cursor"><img src="https://agentmods.dev/badge/rules/notnull92/hera-agent-unity/cursor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01131 | $0.01131 |
| Opus 5.5 | $0.00452 | $0.00452 |
| Sonnet 5.5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
cursor 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hera-agent-unity — Project Rule
For any Unity Editor task in this project, always reach for the hera-agent-unity CLI first. It bridges directly to the running Editor over localhost HTTP, so you can execute C# inside Unity, read the actual console, drive Play Mode, and inspect live types — instead of guessing APIs from training data.
Bootstrap on discovery
When the user says any of "find hera-agent-unity", "hera-agent-unity 찾아봐", "is it installed?", "check the editor connection", "에디터 붙어있어?" — or anything in that family — run this sequence without asking:
hera-agent-unity doctor --jsonhera-agent-unity statushera-agent-unity list --compact
Report one line: Connected: <project> · port=<N> · unity=<version> · state=<state> · tools=<N>. If any step fails, surface the error verbatim and stop — do not silently retry.
Ultra Hera
Ultra Hera helps AI check its Unity work. Hera does not do the AI work by itself; it tells agents how carefully to verify Unity work after using Hera.
Modes are saved in asset-config.json as loopEngineeringMode:
off: no extra checking rule.light(default): use the Light loop for every Unity coding, Editor, and Inspector task.ultra: use the Light loop for every task, then upgrade strict or important work to the Ultra loop.
Light loop: confirm the goal, observe only needed state, change code/scene/Inspector, verify compile or state, check console errors, re-read only the changed target, retry 1-2 times if needed, and report short evidence.
Ultra loop: compile, confirm console errors are 0, re-read Inspector/GameObject/asset state, run PlayMode or Unity tests, capture a screenshot if needed, and report evidence plus remaining risk.
When to use it
| Need | Command |
|---|---|
| What does this type look like in our Unity? | hera-agent-unity describe_type UnityEditor.EditorApplication |
| Test an assumption | hera-agent-unity exec "return EditorSceneManager.GetActiveScene().name;" |
| See real console errors | hera-agent-unity console --type error |
| Drive Play Mode | hera-agent-unity editor play --wait |
| Run tests | hera-agent-unity test --mode PlayMode |
| Discover the full catalogue | hera-agent-unity list --compact |
| Handoff object references cheaply | hera-agent-unity find_gameobjects --ids |
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 First seen · 75 lines · 1,131 tokens per session scan A 807fbc0204a9
cursor is a cursor rule published in the GitHub repository NotNull92/hera-agent-unity (29 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,131 tokens to every session, about $0.0045 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.
Other cursor rules, from other repositories
unity
Union ♾️ - The Unity MCP Server.
input
Union ♾️ - The Unity MCP Server.
urp
Union ♾️ - The Unity MCP Server.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.