Install
$ agentstack add skill-frabcd-codex-ai-game-studio-setup-unreal ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Set up Unreal Engine
Run the core doctor. Inspect the .uproject, engine association, source versus Blueprint project, installed editor/toolchain, OS/architecture, GPU-backed screenshot capability, disk needs, current plugins, and existing Unreal MCP host.
Default to Apache-2.0 IvanMurzak/Unreal-MCP at the immutable descriptor commit. GenOrca/unreal-mcp is the selectable alternative. Explain that editor control can execute console commands, reflection calls, Python, and project writes; it is high-trust local automation and must not ship enabled in a production game.
Create pack plan unreal --project --output . Select the alternative only with --provider GenOrca/unreal-mcp. Configure a local server executable only by absolute path plus verified SHA-256. Present exact actions, large/plugin downloads, licenses, permissions and RCE-class risks, backups, expiry, rollback operations, and digest. Wait for the user to repeat the displayed digest verbatim. Apply only with pack apply --project --plan --confirmed-digest . Verify with pack doctor, plugin load evidence, and a read-only ping; do not open or mutate the editor merely to prove setup.
Only one Unreal MCP may be active. Adapter replacement and rollback each require their own confirmed plans.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: frabcd
- Source: frabcd/codex-ai-game-studio
- License: MIT
- Homepage: https://frabcd.github.io/codex-ai-game-studio/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.