A set of project rules for using NexusLink, a tool connection for working with Unreal Engine assets and related game-development data. It requires the agent to discover available tools and asset paths before reading or changing anything.

Use it when working with Unreal Engine blueprints, widgets, materials, behavior trees, gameplay systems, Lua, or other listed assets through NexusLink.

It prevents guessed tool names and file paths, and provides a fixed sequence for safe asset operations.

AIRules — Cursor rule for Cursor by bytepine/NexusLink

Install

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.

Clone the repo

git clone --depth 1 https://github.com/bytepine/NexusLink

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/bytepine/nexuslink/airules/github.svg)](https://agentmods.dev/rules/bytepine/nexuslink/airules)

Your own site

<a href="https://agentmods.dev/rules/bytepine/nexuslink/airules"><img src="https://agentmods.dev/badge/rules/bytepine/nexuslink/airules/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/bytepine/nexuslink/airules"><img src="https://agentmods.dev/badge/rules/bytepine/nexuslink/airules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,253 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00026	$0.02253
Opus 5.5	$0.00010	$0.00901
Sonnet 5.5	$0.00005	$0.00451
Haiku 4.5	$0.00003	$0.00225

Measured 4d ago against content hash 3cd92d5a756e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

AIRules 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.

Resources/AIRules.mdc · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NexusLink AI Workflow (IDE-side Rule)

Division of labor with MCP handshake instructions

InitializeInstructions (UE handshake): capability routing table, meta-tool constraints, read/write naming.

This Rule (IDE-side): enforce discover tools → find paths → read/write; forbid guessing cap names/paths; fill project-level PathFilter prefixes.

Source: Plugins/NexusLink/Resources/AIRules.mdc — diff generic sections into your project copy after plugin upgrades.

1. Four-step flow (required)

For UE assets / PIE / blueprints / Widget / material / behavior tree / GAS, call MCP this turn first, then answer. UnLua is NexusLinkExt: discover those caps with SearchCapabilities when that plugin is loaded.

Step	Tool	Notes
1 Discover capability	`SearchCapabilities`	Skip when cap name is known; otherwise `Query` with 1–2 narrow words (e.g. `blueprint variable`, `runtime actor`, `behavior tree`); no business feature names, asset names, or over-broad single tokens (see §2)
2 Discover asset paths	`SearchAsset`	Requires `AssetType` + functional `PathFilter`; top-level `Assets`; typed search adds top-level `RecommendedGet`/`RecommendedManage` — prefer those in step 3
3 Read/write	`get_asset_` / `manage_asset_` / `list_runtime_*` etc.	`AssetPath` only from `assets[].path`; prefer `RecommendedGet`/`RecommendedManage`; when lists include `<k>_defaults`, missing fields equal that value (`{defaults,entry}`)
4 Persist	`SaveAsset` or manage `bSaveToDisk=true`	Required after disk asset edits; BP/ABP/WBP may also pass `bCompile=true`

Meta-tools SearchCapabilities, CallCapability, SubmitFeedback must use MCP tools/call directly — not CallCapability(Capability="SearchCapabilities", …).

Editor UI uses GetEditorSlate / CaptureEditorSlate / InteractEditorSlate; use only returned Ref identifiers. Local tests use ControlEditorAutomation / ListEditorAutomationTests; compile uses CompileEditorLiveCoding. Start once, then query GetEditorOperation with OperationId; WaitSeconds is capped at 30. State=Completed describes execution, so inspect Result.Outcome or per-test outcomes. Cancelling a request ends its wait; explicitly stop supported operations. Never retry writes after disconnect or timeout. These operations cannot join Calls[] atomic batches. Discovery publishes Execution backend reasons and outputSchema.

Read the full file on GitHub · 120 lines

Changes

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 Changed · +2 lines 3cd92d5a756e
8d ago Changed 56e128dae286
9d ago Changed 8f4cfe8a196d
10d ago Changed · +1 lines 47e6c578b0b3
17d ago Changed 6c7afab50c20
1mo ago Changed a25db6bf0174
1mo ago Changed · +1 lines 9760e9b9317a
1mo ago Changed · +1 lines 538eed8cf744
1mo ago Changed 88f2c0349cf9
1mo ago First seen · 115 lines · 26 tokens per session scan A 4327932528cd

Subscribe to this mod's changes

AIRules is a cursor rule published in the GitHub repository bytepine/NexusLink (9 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 2,253 once invoked, about $0.0001 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 2026-08-31.

Game development ai-tools blueprints mcp model-context-protocol unreal-engine unrealengine

AIRules

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

NexusLink AI Workflow (IDE-side Rule)

1. Four-step flow (required)

What this file has done since we first saw it

Other cursor rules, from other repositories

monobehaviour-lifecycle

minimax-m2-core

security-best-practices

ponytail

angular-20

dev-standard