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 Italink/UnrealClientProtocol --skill unreal-nodecode-commongit clone --depth 1 https://github.com/Italink/UnrealClientProtocolWrote 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/italink/unrealclientprotocol/unreal-nodecode-common)<a href="https://agentmods.dev/skills/italink/unrealclientprotocol/unreal-nodecode-common"><img src="https://agentmods.dev/badge/skills/italink/unrealclientprotocol/unreal-nodecode-common/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/italink/unrealclientprotocol/unreal-nodecode-common"><img src="https://agentmods.dev/badge/skills/italink/unrealclientprotocol/unreal-nodecode-common.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00909 |
| Opus 5 | $0.00028 | $0.00454 |
| Sonnet 5 | $0.00011 | $0.00182 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
unreal-nodecode-common 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NodeCode Common Rules
NodeCode is the unified text-based representation used by UCP to read/write node graphs across Materials, Blueprints, Niagara scripts, and Widget trees. All domain-specific editing skills share the same underlying diff/apply engine. This document describes the common behaviors that apply to all of them.
API
CDO: /Script/UnrealClientProtocolEditor.Default__NodeCodeEditingLibrary
| Function | Params | Description |
|---|---|---|
Outline |
AssetPath |
List available sections for an asset |
ReadGraph |
AssetPath, Section |
Read a section's text representation. Empty Section = all. |
WriteGraph |
AssetPath, Section, GraphText |
Write a section. Triggers recompile/refresh as appropriate. |
Node ID Format
- Existing nodes:
N_<base62>— 22-character Base62-encoded GUID. ReadGraph always outputs this form. - New nodes:
N_new<int>— temporary ID for nodes you are creating (e.g.N_new0,N_new1). The system assigns a real GUID after WriteGraph.
Connection Syntax (Graph Sections)
Connections are declared on the source (output) node, indented with >:
> OutputPin -> N_<target>.InputPin # named output to named input
> OutputPin -> [GraphOutput] # output to graph-level output
> -> N_<target>.InputPin # single-output node (omit pin name)
> -> N_<target> # single-output to single-input
Domain-specific pin names and graph outputs vary — see each editing skill for details.
Key Rules
- Preserve node IDs — existing nodes use
N_<base62>IDs that encode their GUID. Always keep them unchanged when writing back. UseN_new<int>only for genuinely new nodes. - ReadGraph before WriteGraph — always read first to understand the current state.
- Undo support — all WriteGraph operations are wrapped in transactions and support Ctrl+Z.
- Incremental diff — WriteGraph only modifies nodes/connections/properties that actually changed. Unchanged parts are left intact.
- Properties are additive, not resetting — WriteGraph only modifies properties that appear in
{...}. Omitting a property does not reset it to its default value; the existing value is preserved. To change a property back to default, you must write it explicitly (e.g.{Period:1.000000}to reset Period). This is critical when correcting previously set non-default values. - Verify all node IDs before writing — every
N_<id>referenced in> ->connection lines must be defined as a node in the same graph. Referencing an undefined ID silently drops that connection.
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.
- 10d ago First seen · 68 lines · 56 tokens per session scan A 856bb0138989
unreal-nodecode-common is a skill published in the GitHub repository Italink/UnrealClientProtocol (125 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 909 once invoked, about $0.0003 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
roblox-luau-core
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.
roblox-audio
Use when implementing Roblox audio playback, spatial sound, music, sound effects, SoundGroups, or dynamic audio effects.
roblox-camera
Use when scripting Roblox camera behavior, CFrame placement, screen raycasts, first or third-person views, or cutscenes.
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.
roblox-lighting
Use for Roblox lighting, atmosphere, day/night, or post-processing effects.
roblox-localization
Use when implementing Roblox multi-language support, translation tables, auto-translation, locale-specific content, or region detection.