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 sideshowroberto/vfx-agent-toolkit --skill unreal-project-preflightgit clone --depth 1 https://github.com/sideshowroberto/vfx-agent-toolkitWrote 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/sideshowroberto/vfx-agent-toolkit/unreal-project-preflight)<a href="https://agentmods.dev/skills/sideshowroberto/vfx-agent-toolkit/unreal-project-preflight"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/unreal-project-preflight/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/sideshowroberto/vfx-agent-toolkit/unreal-project-preflight"><img src="https://agentmods.dev/badge/skills/sideshowroberto/vfx-agent-toolkit/unreal-project-preflight.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 | $0.00067 | $0.04033 |
| Opus 5.5 | $0.00027 | $0.01613 |
| Sonnet 5.5 | $0.00013 | $0.00807 |
| Haiku 4.5 | $0.00007 | $0.00403 |
Grade A, and why
unreal-project-preflight scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Dependencies:** Unreal Engine 5.8 (launcher install), Python 3.10+, curl on PATH, UE 5.8 native MCP on the project's configured port for `--live` How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unreal-project-preflight
Version: 1.0.1
Last Updated: 2026-09-08
Dependencies: Unreal Engine 5.8 (launcher install), Python 3.10+, curl on PATH, UE 5.8 native MCP on the project's configured port for --live
Status: Production-ready (probed against two real 5.8 projects on 2026-09-08)
Why this skill exists
Every Unreal build session that went wrong in the same way: the plan was approved, the agent started creating things, and the first real step failed because a plugin was off (ImagePlate, ProceduralVegetationEditor, MovieRenderPipeline), a project setting was not on (Nanite Foliage for MegaPlants, SM6 for Nanite), or the fix needed an editor restart that then lost unsaved component edits. The unreal-* skills document APIs, not the switches those APIs sit behind.
This skill puts ONE pass between "plan approved" and "step 1": read what the project actually has, list every change the plan needs, apply them as a batch, restart ONCE, read the result back, and only then start building.
CRITICAL: MANDATORY FIRST STEP
Run the checker against the project the plan targets before writing any Step 0 by hand. Never list prerequisites from memory.
# The editor is running: ask it which project it has open and read plugins back
python <skill-dir>/scripts/ue_preflight.py --live --features <feature,list> --plan-block
# The editor is closed: check the files the next launch will load
python <skill-dir>/scripts/ue_preflight.py --project <path>/Show.uproject --features <feature,list> --plan-block
Read the project : line. If --live reports the editor has a DIFFERENT
project open than the one the plan targets, stop: the live readings describe
the other project, and building would land in the wrong place. (This
happened during the skill's own commissioning: the production project was
the intended target, the editor had a dev-tests project open.)
Standard Workflows
Workflow 1: The ritual (where it sits in a plan)
- Plan is written and approved (vfx-plan, goal-criteria-planning, or a plain plan in chat).
- Derive the feature list from the plan's steps. Every step that names
an Unreal subsystem maps to one or more catalog features
(
--list-features). "Forest with a road through it" is at leastpcg,megaplants,landscape-patchand usuallymrqfor the check render. Add ad-hoc--requirespecs for anything the catalog lacks. - Run the checker (above) and paste its
--plan-blockoutput into the plan as Step 0 - Environment preflight. The block already contains the change list, the restart plan and the feature notes. - Get the operator's OK on Step 0 - plugin toggles and renderer settings are project-wide and land in source control.
- Execute Step 0 as written: save, operator closes the editor,
--apply, relaunch,--livere-run must report0 need changes. That read-back is the gate; a summary line with anything but 0 means Step 1 does not start. - Only now Step 1.
What ships with it
2 files 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.
- today First seen · 320 lines · 67 tokens per session scan A 09d9ab73a306
unreal-project-preflight is a skill published in the GitHub repository sideshowroberto/vfx-agent-toolkit (16 stars, last pushed 22d ago), licensed MIT. It adds 67 tokens to every session and 4,033 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-02.
Other skills, from other repositories
usd-tools
Infrastructure skill — low-level OpenUSD scene inspection and validation: read layer stacks, traverse prims, validate USD schemas. Use when working directly with raw USD files (usda, usdc, usdz) or verifying USD compliance. Not for Maya-specific USD export — use maya-pipelineexportusd for that. Not for full DCC…
spatial-interchange
Plan deterministic coordinate-axis and unit conversions between DCCs, engines, and interchange formats from explicit right/up/forward axes and meters-per-unit values.
game-level-layout
Game level layout review helpers for editor contexts.
ue5-blueprint-workflow
UE5.6/UE5.7 Blueprint graph workflow for feature implementation, input events, node wiring, and graph validation. Use when requests involve adding Blueprint logic, keyboard input behavior, function chains, event graph edits, or pin-level connection guidance.
ue57-camera-transform
Set, get, and animate UE Editor viewport camera and CameraActor transforms safely. Prevents the common Rotator positional-argument trap (roll,pitch,yaw vs pitch,yaw,roll). Use when AI needs to: (1) move or rotate the viewport camera, (2) set a CameraActor's transform, (3) look-at a target location, (4) orbit around an…
ue57-viewport-capture
Capture UE viewport screenshots (color, depth, normal buffers) and build AI analysis context. Use when AI needs to: (1) take a screenshot of the current viewport, (2) capture depth/normal maps alongside color, (3) analyze scene composition/lighting/performance visually, (4) get viewport image + camera transform for…