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.
git clone --depth 1 https://github.com/HybridAIOne/hybridclawnpx agentmods add skills/hybridaione/hybridclaw/video.from-scriptWrote 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/hybridaione/hybridclaw/video.from-script)<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.
<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>- 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 | $0.00023 | $0.01532 |
| Opus 5 | $0.00012 | $0.00766 |
| Sonnet 5 | $0.00005 | $0.00306 |
| Haiku 4.5 | $0.00002 | $0.00153 |
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.
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 — 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
- Confirm the user has provided an avatar source, voice id, and final script.
- Run public-facing marketing, sales, training, or onboarding copy through
/brand-voicebefore starting a credit-consuming render. - Use
planif the request is vague or needs an explicit risk summary. - Use
startafter the operator grants the exact credit-consuming render. Return thejobIdto the user because HeyGen renders asynchronously. - Use
status --job-id <id>to poll conservatively. Add--downloadonly after the status is complete or when the user asks you to fetch the MP4. - Use
render --waitonly 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:
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.
- 7d ago First seen · 180 lines · 23 tokens per session scan A a60d2259f777
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.
Other skills, from other repositories
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.".
figure-composer
Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via deriveoutlineprompt (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → render each panel with paneltask (loading figure-style), one at a time or…
design_creator
Structured workflow for creating professional designs — slide decks, documents, landing pages, app mockups, and motion storyboards.
video_guide
Guidance for generating videos and animating images.
vision_guide
Guidance for using webcam, screen capture, and image analysis.
lilbee-mcp
Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…