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 leynos/visual-storytelling-skills --skill media-projectgit clone --depth 1 https://github.com/leynos/visual-storytelling-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/leynos/visual-storytelling-skills/media-project)<a href="https://agentmods.dev/skills/leynos/visual-storytelling-skills/media-project"><img src="https://agentmods.dev/badge/skills/leynos/visual-storytelling-skills/media-project/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/leynos/visual-storytelling-skills/media-project"><img src="https://agentmods.dev/badge/skills/leynos/visual-storytelling-skills/media-project.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 | $0.00056 | $0.01263 |
| Opus 5 | $0.00028 | $0.00632 |
| Sonnet 5 | $0.00011 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
media-project 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 11d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media-project OpenShot handoff
Use this skill when packaging selected generated clips into an OpenShot project
with the media-project command. The command is expected to be installed at
the system tool level before this skill is used, normally with uv tool install.
Do not assume the story project contains the media-project source tree. The
story project normally contains only generated media, metadata, prompts, and
editor handoff outputs.
Hard stop
Before running media-project package-openshot, verify both commands exist:
command -v media-project
command -v ffprobe
If media-project is absent, stop immediately and report that the command must
be installed system-wide with uv tool install before packaging can proceed.
Do not look for repository-local source directories or try to run the command
through a project checkout.
If ffprobe is absent, stop immediately. Do not run the packager, do not write
a minimal .osp, and do not tell the user the project is packaged. Report that
ffprobe is required because OpenShot playback depends on full FFmpeg reader
metadata in both files[] and clips[].reader.
Inputs
Only package a project after video-generator has produced reviewed local
media and these project-root-relative files:
generated/assembly_order.mdgenerated/generation_log.md- every selected local video file named by those tables
Preferred generated/assembly_order.md columns are:
| Column | Meaning |
|---|---|
Order |
Final timeline order. |
Shot ID |
Stable shot identifier. |
Sub-clip |
Sub-clip identifier. |
Selected clip |
Project-root-relative local video path. |
Boundary after |
Edit-boundary or transition intent after the clip. |
Notes |
Editor handoff notes. |
Some older assembly files may use File instead of Selected clip or
Boundary (next) instead of Boundary after. Treat those as compatibility
aliases only when the installed tool version documents support for them.
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.
- 11d ago First seen · 141 lines · 56 tokens per session scan A f02a201dd244
media-project is a skill published in the GitHub repository leynos/visual-storytelling-skills (6 stars, last pushed 1mo ago), licensed ISC. It adds 56 tokens to every session and 1,263 once invoked, about $0.0003 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
wavespeed
Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one wavespeed run call.
1688-ecommerce-video-generation-editing
A workflow for generating and editing 1688 e-commerce videos, including videos made from text, images, existing video, or audio.
1688-ecommerce-image-generation-editing
A tool for creating and editing product images for 1688, Alibaba's Chinese wholesale marketplace, and similar sales channels. It can work from text or reference images to produce product pages, advertisements, posters, and social-media visuals.
ai-model-expert-1688-ecommerce-image-generation-editing
An AI image-generation and editing workflow for 1688 e-commerce content, using text or reference images to guide the result. 1688 is a Chinese online wholesale marketplace.
ai-model-expert-1688-ecommerce-video-generation-editing
An AI tool workflow for creating and editing 1688 e-commerce videos from text, images, videos, or audio. 1688 is a Chinese online wholesale marketplace.
ai-model-expert-ai-ad-video
AI video production support for turning text, images, videos, or audio into advertising and other commercial videos.