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 moonvalley-mareygit 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/moonvalley-marey)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/moonvalley-marey"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/moonvalley-marey/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/moonvalley-marey"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/moonvalley-marey.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 | $0.00201 | $0.05030 |
| Opus 5 | $0.00101 | $0.02515 |
| Sonnet 5 | $0.00040 | $0.01006 |
| Haiku 4.5 | $0.00020 | $0.00503 |
Grade A, and why
moonvalley-marey 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 8d 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 — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moonvalley Marey
Marey is Moonvalley's generative video model, aimed at professional filmmakers, studios, and brand teams that need AI video they can put through legal review. Its differentiator is not raw fidelity — it is provenance: Moonvalley markets Marey as trained exclusively on owned or licensed footage, and pairs it with a set of director-style controls. This skill helps an agent decide when Marey is the right tool, use it correctly, and — critically — represent its legal posture accurately rather than repeating marketing.
Verification date for all volatile facts below: 2026-07-10. Re-check version, pricing, endpoints, and the terms of service before relying on any dated claim.
Company and model status (verified 2026-07-10)
- Company: Moonvalley (moonvalley.com), an "imagination research company." Marey was built with the animation studio Asteria. Moonvalley raised an additional $84M in July 2025 (investors incl. General Catalyst, CAA, Comcast Ventures, CoreWeave, Khosla Ventures, Y Combinator), reportedly ~$154M total. The company is active and funded — not shut down or pivoted. [businesswire, variety, techcrunch — see Sources]
- Model: The publicly available production model is Marey Realism v1.5. It first entered public availability July 2025 after an earlier limited release (March 2025). [techcrunch, fal]
- Platform: Moonvalley also markets Voyager, a higher-end platform/UI that exposes Marey's fuller control set for studio workflows. [businesswire]
- Named after Étienne-Jules Marey, a chronophotography pioneer — a signal of the "cinematography-first" brand positioning.
Treat "v1.5" as volatile. Moonvalley has publicly promised further controls (lighting, deeper object trajectories, character libraries); a newer point release may exist by the time you read this.
Documented capabilities and hard limits
These are documented on the fal model pages and Moonvalley/partner docs (verified 2026-07-10). Distinguish them from marketing claims below.
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.
- 8d ago First seen · 376 lines · 201 tokens per session scan A ff0c1ae6265e
moonvalley-marey is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 1mo ago), licensed MIT. It adds 201 tokens to every session and 5,030 once invoked, about $0.0010 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-audio-polish-mixer
Produces a task-local audio-polished preview or output from an existing cut, applying loudness normalization, optional noise reduction, fades, muting, and voice-first mix policy.
cliptalk-broll-overlay-editor
Adds relevant B-roll or cutaway overlays to an existing timeline while preserving the primary audio and making the result reviewable before final export.
cliptalk-cover-intro-composer
Creates task-local cover candidates and composes the confirmed cover into the beginning of the current output as a short intro, keeping cover selection separate from video editing.
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.