video-generation

video-generation is a skill for Claude Code from Galbaz1/video-research-mcp. It costs 44 tokens per session (1,911 once invoked), scanned A, original, MIT.

A guide for generating AI video from text or images with Veo or Sora, including extending existing clips.

In plain words
What is it for?
It is for text-to-video, image-to-video, video extension, style-consistent clips, and selecting between providers for production needs.
Why use it?
It helps choose a video generator and a draft-to-final workflow based on the needs of the shot.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; positional $N argument.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/fausto_home/.claude/skills/sora/scripts/sora_direct.py.

Part of the gr plugin — 12 skills, 17 commands, 7 agents shipped together

Good fit It is for text-to-video, image-to-video, video extension, style-consistent clips, and selecting between providers for production needs.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Galbaz1/video-research-mcp
Claude Code
/plugin install gr

Made for: Claude Code.

Or install gr, the plugin that ships this one along with the rest of its 12 skills, 17 commands, 7 agents.

Wrote 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.

agentmods badge for video-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/video-generation/github.svg)](https://agentmods.dev/skills/galbaz1/video-research-mcp/video-generation)
Your own site
<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/video-generation"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/video-generation/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.

agentmods 80×15 button for video-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/video-generation"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/video-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,911 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01911
Opus 5 $0.00022 $0.00955
Sonnet 5 $0.00009 $0.00382
Haiku 4.5 $0.00004 $0.00191

Measured 11d ago against content hash 8b22bb1002e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

video-generation 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.

skills/video-generation/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Generation

Generate AI video using Veo (MCP tools) or Sora (direct API script). This skill covers provider selection, generation modes, defaults, and the draft-to-final workflow.

For full tool references, model IDs, camera reliability data, and negative prompt blocks, see references/provider-details.md.

Provider Selection

Choose before writing prompts.

Need Provider Why
Native audio, 4K output, style/asset references, video extension Veo Veo 3.1 has the richer media-control surface
1080p production, text-heavy scenes, clean draft/final model split Sora sora-2 drafts + sora-2-pro finals is the most reliable loop
High-value hero shot, uncertain which provider wins Both Generate with both, pick winner from review evidence

Decision rules:

  1. Veo when: native audio matters, you need 4K, you have style-anchor images for cross-clip consistency, or you need to extend an existing clip.
  2. Sora when: 1080p is sufficient, the scene has on-screen text, or the draft-to-pro upgrade path saves iteration time.
  3. Both when: the shot is expensive to reshoot and the extra cost of a bakeoff is justified.

Generation Modes

Text-to-Video

Prompt describes the scene. Both providers support this.

  • Veo: mcp__veo__generate_video -- supports number_of_videos (1-4) for multi-take
  • Sora: sora_direct.py create-and-poll -- single generation per call

Image-to-Video (I2V)

Animate a static image. Source image quality is critical.

  • Veo: mcp__veo__animate_image -- absolute path to source image required
  • Sora: sora_direct.py create-and-poll --input-reference -- auto-resizes/crops source to match output size

Video Extension

Continue an existing clip with new content.

  • Veo: mcp__veo__extend_video_clip -- Veo 3.1 only, continues from last second
  • Sora: sora_direct.py extend --id <video_id> -- extends by prompt

Styled Generation (Veo only)

Read the full file on GitHub · 175 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 175 lines · 44 tokens per session scan A 8b22bb1002e6

Subscribe to this mod's changes

video-generation is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,911 once invoked, about $0.0002 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 2026-08-30.