video.from-script

video.from-script is a skill for Claude Code from HybridAIOne/hybridclaw. It costs 23 tokens per session (1,532 once invoked), scanned A, original, MIT.

A service for rendering approved scripts as avatar-and-voice videos through HeyGen. It takes an avatar or image, a voice ID, and final script text, then produces an MP4 video.

In plain words
What is it for?
Use it to create marketing, sales, training, or onboarding videos with a selected avatar, voice, and script.
Why use it?
It handles the waiting and file retrieval involved in an asynchronous video-rendering job. It also keeps the HeyGen API key out of the working files and commands.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 skills/skill-creator/scripts/quick_validate.py skills/video.from-script.

Good fit Use it to create marketing, sales, training, or onboarding videos with a selected avatar, voice, and script.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/HybridAIOne/hybridclaw
agentmods
npx agentmods add skills/hybridaione/hybridclaw/video.from-script

Made for: Claude Code.

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.from-script

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridaione/hybridclaw/video.from-script/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/video.from-script)
Your own site
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/video.from-script"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/video.from-script/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.from-script

Your own site · 80×15
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/video.from-script"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/video.from-script.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,532 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00023 $0.01532
Opus 5 $0.00012 $0.00766
Sonnet 5 $0.00005 $0.00306
Haiku 4.5 $0.00002 $0.00153

Measured 7d ago against content hash a60d2259f777, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

video.from-script 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (video-from-script.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.from-script/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video From Script

Use this skill when the user wants an avatar video from three concrete inputs: an avatar or image source, a voice id, and approved script text. The backing provider is HeyGen Direct API via the bundled heygen adapter.

Scope

  • plan avatar video generation from script text
  • start a HeyGen video generation job and return the job id immediately
  • poll job status until it is completed, failed, or still rendering
  • download the completed MP4 into .generated-videos
  • keep HeyGen API keys behind gateway secret injection

Template videos, free-form prompt-to-video, public publishing, social posting, and custom avatar training are outside this skill. Use video-generation for native Sora/Veo prompt videos and heygen for lower-level HeyGen API work. Polling is the completion transport implemented for R55.2; webhook callbacks belong in a provider/gateway adapter if that transport is added later.

Default Workflow

  1. Confirm the user has provided an avatar source, voice id, and final script.
  2. Run public-facing marketing, sales, training, or onboarding copy through /brand-voice before starting a credit-consuming render.
  3. Use plan if the request is vague or needs an explicit risk summary.
  4. Use start after the operator grants the exact credit-consuming render. Return the jobId to the user because HeyGen renders asynchronously.
  5. Use status --job-id <id> to poll conservatively. Add --download only after the status is complete or when the user asks you to fetch the MP4.
  6. Use render --wait only when the user explicitly wants the agent to wait for the final MP4 in the same run.

Do not run parallel render bursts. HeyGen quotas are tight and account/plan dependent.

Command Contract

Run the helper with Node:

node skills/video.from-script/video-from-script.cjs --help

In packaged agent workspaces this skill can be mounted with a hyphenated directory name. If the command above fails with Cannot find module, run:

Read the full file on GitHub · 180 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. 7d ago First seen · 180 lines · 23 tokens per session scan A a60d2259f777

Subscribe to this mod's changes

video.from-script is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,532 once invoked, about $0.0001 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.