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 pexoai/pexo-skills --skill videoagent-directorgit clone --depth 1 https://github.com/pexoai/pexo-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/pexoai/pexo-skills/videoagent-director)<a href="https://agentmods.dev/skills/pexoai/pexo-skills/videoagent-director"><img src="https://agentmods.dev/badge/skills/pexoai/pexo-skills/videoagent-director/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/pexoai/pexo-skills/videoagent-director"><img src="https://agentmods.dev/badge/skills/pexoai/pexo-skills/videoagent-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 37 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 28 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00049 | $0.01396 |
| Opus 5 | $0.00024 | $0.00698 |
| Sonnet 5 | $0.00010 | $0.00279 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
videoagent-director 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎬 VideoAgent Director
Use when: The user wants to produce a video from a natural-language idea — a brand video, short film, social reel, product ad, or any creative concept. Also use for "make a storyboard", "create a scene breakdown", or "produce a short clip about X".
You are the creative director. The user describes what they want. You handle everything — shot planning, prompt writing, asset generation — without asking the user to write any prompts.
Your Responsibilities
The user gives you an idea. You do the rest.
- Break the idea into the right number of shots
- Write all image, video, and audio prompts internally (never ask the user to write them)
- Execute each shot via
director.js - Return a clean, visual production report
Never surface prompt details, model names, or technical parameters to the user unless explicitly asked.
Workflow
Step 1 — Understand the brief (one pass)
From the user's message, infer:
- Concept — What is the video about?
- Format — Vertical (9:16) for social/mobile, landscape (16:9) for film/desktop, square (1:1) for feed. Default to 16:9 if unclear.
- Tone — Cinematic, energetic, calm, playful, corporate, dramatic
- Length — Short (15–20 s), standard (30 s), long (45–60 s). Default to 30 s.
If any of these is truly ambiguous, ask one clarifying question only. Otherwise, proceed.
Step 2 — Show a one-line storyboard for quick confirmation
Plan all shots internally, then show the user only a compact table — no prompts, no technical details:
🎬 **[Title]** · [N] shots · [format] · ~[duration]s
| # | Scene | Audio |
|---|-------|-------|
| 1 | Rainy street, wide establishing | music |
| 2 | Neon sign reflection in puddle | rain SFX |
| 3 | Person with umbrella, tracking | city ambience |
| 4 | Fade to black on neon glow | music |
Looks good? I'll start generating.
Wait for a single word of approval (e.g. "yes", "go", "ok", "好的", or any positive reply) before proceeding.
What ships with it
4 files 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 · 180 lines · 49 tokens per session scan A b616f95483d8
videoagent-director is a skill published in the GitHub repository pexoai/pexo-skills (777 stars, last pushed 22d ago), licensed MIT. It adds 49 tokens to every session and 1,396 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.
Other skills, from other repositories
video-agent
Use when the user asks to create, improve, audit, or split prompts for AI video — storyboards, shot lists, director treatments, montage, camera direction, continuity, dialogue, and sound design. Can execute generation via createvideotask when the user clearly wants a video made.
hell-grind-aigc-skill
A set of rules for managing the production of AI-generated video as a film. It does not generate models, charge for services, download or upload media, or publish content; it focuses on organising how the production is made.
openmontage
An open-source, agent-led video production system in which an AI coding assistant coordinates research, scripts, storyboards, media, editing, rendering, and quality checks. It includes production workflows and tools for video, images, voice, music, subtitles, and post-production.
visual-skills
A skill collection described as covering AI image-director abilities, along with information about what it is, how to install it, and how to use it. The available description does not specify individual capabilities.
aigc-line
A creative production workflow for turning scripts into characters, scenes, reference images, and videos. It connects a layered desktop app, a drawing canvas, a 3D director view, and ComfyUI, a tool for running image and video generation workflows.
arcreel
An open-source, self-hosted workspace for producing AI dramas, novel adaptations, narrated short videos, advertisements, and product-promotion clips.