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 NAJEMWEHBE/unreal-ai-connection --skill driving-unrealgit clone --depth 1 https://github.com/NAJEMWEHBE/unreal-ai-connectionWrote 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/najemwehbe/unreal-ai-connection/driving-unreal)<a href="https://agentmods.dev/skills/najemwehbe/unreal-ai-connection/driving-unreal"><img src="https://agentmods.dev/badge/skills/najemwehbe/unreal-ai-connection/driving-unreal/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/najemwehbe/unreal-ai-connection/driving-unreal"><img src="https://agentmods.dev/badge/skills/najemwehbe/unreal-ai-connection/driving-unreal.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 | $0.00269 | $0.01661 |
| Opus 5 | $0.00134 | $0.00830 |
| Sonnet 5 | $0.00054 | $0.00332 |
| Haiku 4.5 | $0.00027 | $0.00166 |
Grade A, and why
driving-unreal 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 12d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving Unreal Engine via the unreal-ai-connection MCP tools
This skill is the know-how layer for the unreal-ai-connection plugin. The plugin exposes ~105 UE
editor-automation tools; this file tells you how to operate them — the chaining order, the
verification checkpoints, and the failure modes. Deep step-by-step recipes and the full UE-quirk
table live in reference.md; read it when executing a specific workflow.
Tools are called as mcp__unreal-ai-connection__<name>. Below, names are written bare for brevity.
Before you touch any tool
- Confirm the bridge is live. The UE plugin binds
127.0.0.1:18888. A cold editor launch takes ~2 minutes to bind; warm is seconds. Calllist_toolsfirst — if it returns the catalog, you are connected. Do not assume a tool exists; the livelist_toolsoutput is the source of truth. - Establish a clean baseline. For anything that places actors, plan an idempotent re-run: prefix
your actor labels (e.g.
Test_*) and start the workflow by deleting that prefix viafind_actors_by_class+delete_actor, so repeated attempts don't pile up duplicates.
Cross-cutting operating patterns (apply to every workflow)
These rules matter more than any single recipe. Internalize them.
-
Actor targeting is hybrid. Actor-targeting tools accept either a display label or an FName. Label is tried first. If a label is ambiguous you get an
ambiguous_actorerror listing candidate FNames — retry with a specific FName. Don't guess; read the candidates back. -
Verify visually, and pick the right capture tool. Three ways to capture, with different trade-offs:
render_camera_to_png— off-screen render to a render target. Deterministic; use this for headless/automated verification. Provide an absolute output path whose parent exists.get_viewport_screenshot/take_high_res_screenshot— capture the active viewport. Can return a frozen frame if the editor window is backgrounded (the viewport stops pumping render frames). Keep the editor foreground if you rely on these.screenshot_actor— convenience wrapper that frames and renders a single actor. After any structural step (placement, material apply, lighting), capture and look before adding detail. Don't build blind.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 101 lines · 269 tokens per session scan A b4b2e962cff7
driving-unreal is a skill published in the GitHub repository NAJEMWEHBE/unreal-ai-connection (9 stars, last pushed 1mo ago), licensed MIT. It adds 269 tokens to every session and 1,661 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
unreal-playtest-agent
Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.
unreal-pie
Domain skill - Unreal Engine Play-In-Editor (PIE) closed-loop verification. Provides PIE lifecycle control (enter/pause/resume/exit), controlled input injection (no OS dependency), viewport screenshot capture, output log snapshot, performance sampling, and Automation Test execution with async job polling. Use for…
unreal-actors
Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.
unreal-cinematics
Domain skill — Sequencer shot and keyframe orchestration, camera cut tracks, and Movie Render Queue job setup. Use when creating or editing Level Sequences, authoring camera animation, or preparing an MRQ job in Unreal Engine 5. Not for Blueprint scripting (unreal-blueprints) or runtime playback (unreal-runtime).
unreal-fab-assets
Acquire free Fab marketplace content through Unreal Engine's official Fab integration, then verify the imported Content Browser assets. Use when the user asks to find, download, add, or import Fab or Unreal Marketplace assets. Not for arbitrary file imports - use unreal-assets instead.
unreal-metasound
Unreal Engine MetaSound Source authoring through the reflected Builder API: create sources, add typed inputs and exact registered nodes, connect opaque vertex handles, set defaults, inspect nodes, build, save, and validate. Use for procedural audio graphs in Unreal Engine 5.4+. Not for arbitrary asset management or…