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-material-editinggit 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-material-editing)<a href="https://agentmods.dev/skills/italink/unrealclientprotocol/unreal-material-editing"><img src="https://agentmods.dev/badge/skills/italink/unrealclientprotocol/unreal-material-editing/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-material-editing"><img src="https://agentmods.dev/badge/skills/italink/unrealclientprotocol/unreal-material-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 116 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.
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 | $0.00051 | $0.04671 |
| Opus 5 | $0.00026 | $0.02336 |
| Sonnet 5 | $0.00010 | $0.00934 |
| Haiku 4.5 | $0.00005 | $0.00467 |
Grade A, and why
unreal-material-editing 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Material Editing
Material editing covers both material properties (ShadingModel, BlendMode, etc.) via the [Properties] section, and node graph (expression nodes and connections) via the [Material] section. Both use the same unified API.
Prerequisite: UE editor running with UCP plugin enabled.
API
CDO: /Script/UnrealClientProtocolEditor.Default__NodeCodeEditingLibrary
| Function | Params | Description |
|---|---|---|
Outline |
AssetPath |
Returns available sections (Properties, Material, Composite:Name) |
ReadGraph |
AssetPath, Section |
Returns text. Empty Section = all. "Material" = main graph only. |
WriteGraph |
AssetPath, Section, GraphText |
Overwrite section. Auto-recompiles, relayouts, refreshes editor. |
Material Properties
Use the [Properties] section to read/write material-level settings:
[Properties]
ShadingModel: MSM_DefaultLit
BlendMode: BLEND_Opaque
TwoSided: true
OpacityMaskClipValue: 0.333
Common properties:
| Property | Example Values |
|---|---|
ShadingModel |
MSM_DefaultLit, MSM_Unlit, MSM_Subsurface, MSM_ClearCoat |
BlendMode |
BLEND_Opaque, BLEND_Masked, BLEND_Translucent, BLEND_Additive |
MaterialDomain |
MD_Surface, MD_DeferredDecal, MD_LightFunction, MD_PostProcess, MD_UI |
TwoSided |
true, false |
Read with ReadGraph(AssetPath, "Properties"), write with WriteGraph(AssetPath, "Properties", text).
Section Model
| Section | Description |
|---|---|
[Properties] |
Material-level properties (ShadingModel, BlendMode, etc.) |
[Material] |
Complete main graph — all non-composite nodes, read/write as one unit |
[Composite:Name] |
Composite subgraph (physically isolated) |
The [Material] section contains the entire main graph. Output pins are expressed as graph output connections: > RGB -> [BaseColor].
Text Format
[Material]
N_4kVm2xRp8bNw3yLq9dJs MaterialExpressionTextureSample {Texture:"/Game/Textures/T_Wood_BC"}
> RGB -> [BaseColor]
> A -> N_7tHn5cWs1fPx6zMr0gKu.A
N_9aEo3jXv2hQy8bFt4iLw MaterialExpressionScalarParameter {ParameterName:"Roughness", DefaultValue:0.5}
> -> N_7tHn5cWs1fPx6zMr0gKu.B
N_2dGq6lZx4jSa0cHv8kNy MaterialExpressionVectorParameter {ParameterName:"EmissiveColor", DefaultValue:{"R":1,"G":0.5,"B":0}}
> -> N_5fIr7mBz3kTb1eJw9lOa.A
N_7tHn5cWs1fPx6zMr0gKu MaterialExpressionMultiply
> -> [Roughness]
N_5fIr7mBz3kTb1eJw9lOa MaterialExpressionMultiply
> -> [EmissiveColor]
N_0hKt8nDc5lUd2gLx6mPb MaterialExpressionConstant {R:5.0}
> -> N_5fIr7mBz3kTb1eJw9lOa.B
N_3jMv0pFe7nWf4iNz8oCd MaterialExpressionTextureSample {Texture:"/Game/Textures/T_Wood_N"}
> -> [Normal]
N_6lOx2rHg9pYh5kPb1qEf MaterialExpressionTime
> -> N_8nQz4tJi0rAj7mRd3sFg.A
N_8nQz4tJi0rAj7mRd3sFg MaterialExpressionSine {Period:6.283185}
> -> N_1pSb6vLk2tCl9oTf5uGh.B
N_1pSb6vLk2tCl9oTf5uGh MaterialExpressionMultiply
> -> [WorldPositionOffset]
N_4rUd8xNm3vEn0qVh7wIj MaterialExpressionWorldPosition
> -> N_1pSb6vLk2tCl9oTf5uGh.A
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 · 359 lines · 51 tokens per session scan A 5ee456e7da62
unreal-material-editing is a skill published in the GitHub repository Italink/UnrealClientProtocol (125 stars, last pushed 12d ago), licensed MIT. It adds 51 tokens to every session and 4,671 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.