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 calesthio/generative-media-skills --skill virtual-production-icvfxgit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote 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/calesthio/generative-media-skills/virtual-production-icvfx)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/virtual-production-icvfx"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/virtual-production-icvfx/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/calesthio/generative-media-skills/virtual-production-icvfx"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/virtual-production-icvfx.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 | $0.00107 | $0.07760 |
| Opus 5 | $0.00053 | $0.03880 |
| Sonnet 5 | $0.00021 | $0.01552 |
| Haiku 4.5 | $0.00011 | $0.00776 |
Grade A, and why
virtual-production-icvfx 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 9d 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Virtual Production ICVFX
Use this skill when an agent must help make an in-camera VFX plan, diagnose an LED-volume shoot, prepare a stage/rehearsal/QA checklist, or translate production requirements into a practical virtual-production package. It is provider-independent: it does not assume a particular LED vendor, tracking vendor, media server, camera, or render-node brand. It is Unreal-aware because many ICVFX stages use Unreal Engine, nDisplay, Live Link, Camera Calibration, OCIO, Switchboard, Stage Monitor, Timed Data Monitor, Multi-User Editing, Remote Control, and Composure.
Do not use this skill for ordinary offline green-screen post compositing, generic storyboard advice, previs with no stage or camera-tracked final-pixel intent, full game mechanics, or general Unreal gameplay engineering.
Source Posture
Label claims as one of these:
- Documented fact: backed by official documentation, standards, or vendor-neutral technical references.
- Dated engine detail: behavior documented for Unreal Engine documentation pages verified on 2026-07-11. Recheck before making purchase, version-lock, or stage-build decisions.
- Production heuristic: stage practice that is useful but must be tested with the actual camera, lens, LED, processor, tracking, sync, content, and color pipeline.
- Observation to verify: plausible diagnosis that needs a stage test, measurement, or vendor/stage confirmation.
Authoritative sources used for this skill, verified 2026-07-11:
- Epic Games, In-Camera VFX Overview: https://dev.epicgames.com/documentation/en-us/unreal-engine/in-camera-vfx-overview-in-unreal-engine
- Epic Games, nDisplay Overview: https://dev.epicgames.com/documentation/en-us/unreal-engine/ndisplay-overview-for-unreal-engine
- Epic Games, nDisplay Configuration File Reference: https://dev.epicgames.com/documentation/en-us/unreal-engine/ndisplay-configuration-file-reference-for-unreal-engine
- Epic Games, Live Link: https://dev.epicgames.com/documentation/en-us/unreal-engine/live-link-in-unreal-engine
- Epic Games, Timecode and Genlock: https://dev.epicgames.com/documentation/en-us/unreal-engine/timecode-and-genlock-in-unreal-engine
- Epic Games, Synchronization in nDisplay: https://dev.epicgames.com/documentation/en-us/unreal-engine/synchronization-in-ndisplay-in-unreal-engine
- Epic Games, Camera Lens Calibration: https://dev.epicgames.com/documentation/en-us/unreal-engine/camera-lens-calibration-in-unreal-engine
- Epic Games, Color Management with OpenColorIO: https://dev.epicgames.com/documentation/en-us/unreal-engine/color-management-with-opencolorio-in-unreal-engine
- OpenColorIO documentation: https://opencolorio.readthedocs.io/en/latest/
- ACES documentation: https://docs.acescentral.com/
- OSHA Electrical safety topic: https://www.osha.gov/electrical
- OSHA Heat safety topic: https://www.osha.gov/heat-exposure
- OSHA Evacuation Plans and Procedures eTool: https://www.osha.gov/etools/evacuation-plans-procedures
- UK Health and Safety Executive, Event safety: https://www.hse.gov.uk/event-safety/
- W3C WCAG 2.2, Three Flashes or Below Threshold: https://www.w3.org/TR/WCAG22/#three-flashes-or-below-threshold
- FDA Laser Products and Instruments: https://www.fda.gov/radiation-emitting-products/home-business-and-entertainment-products/laser-products-and-instruments
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.
- 9d ago First seen · 445 lines · 107 tokens per session scan A 84b155d30a7f
virtual-production-icvfx is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 7,760 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…