agentmods.dev

create-manual-video

create-manual-video is a skill for Claude Code, Codex from egocen-vivideo/vivideo-toolchain. It costs 57 tokens per session (483 once invoked), scanned A, original, MIT.

A workflow for creating a Vivideo video with a specific underlying AI model, such as Veo, Sora, Kling, or Seedance.

In plain words
What is it for?
Use it to validate a model’s supported settings, create text-to-video or image-to-video jobs, and retrieve the resulting video.
Why use it?
It gives more control when the user has chosen a model or needs options such as image-to-video, duration, resolution, or aspect ratio.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 3mo ago A scan 57 tokens original MIT

Good fit Use it to validate a model’s supported settings, create text-to-video or image-to-video jobs, and retrieve the resulting video.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/egocen-vivideo/vivideo-toolchain/create-manual-video
View source ↗ egocen-vivideo/vivideo-toolchain
Install

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.

Any agent
npx skills add egocen-vivideo/vivideo-toolchain --skill create-manual-video
Clone the repo
git clone --depth 1 https://github.com/egocen-vivideo/vivideo-toolchain

Made for: Claude Code, Codex.

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 create-manual-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/egocen-vivideo/vivideo-toolchain/create-manual-video/github.svg)](https://agentmods.dev/skills/egocen-vivideo/vivideo-toolchain/create-manual-video)
Your own site
<a href="https://agentmods.dev/skills/egocen-vivideo/vivideo-toolchain/create-manual-video"><img src="https://agentmods.dev/badge/skills/egocen-vivideo/vivideo-toolchain/create-manual-video/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 create-manual-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/egocen-vivideo/vivideo-toolchain/create-manual-video"><img src="https://agentmods.dev/badge/skills/egocen-vivideo/vivideo-toolchain/create-manual-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 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 $0.00057 $0.00483
Opus 5.5 $0.00023 $0.00193
Sonnet 5.5 $0.00011 $0.00097
Haiku 4.5 $0.00006 $0.00048

Measured 2mo ago against content hash f9a1681b15ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-manual-video 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 2mo 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/create-manual-video/SKILL.md · 27 lines

What it actually says

Create a manual-mode video

Manual mode sends your prompt straight to one model. Use it when the user picks a model or needs image-to-video.

Workflow

  1. check_configuration → check_account (premium + credits).
  2. Choose a model and read its options. Call list_models with mode: "manual". Each model lists exactly what it accepts:
    • operations (text_to_video, image_to_video, first_last_frame, multiple_images)
    • durations, resolutions, aspect_ratios, styles
    • credits_per_second (for estimate_credits) Only use values from that model's lists. An invalid resolution/duration_seconds/aspect_ratio/style returns a 400 invalid_request whose details.allowed lists the valid values — read it and retry with a valid value.
  3. (Optional) estimate with estimate_credits (mode: "manual", the model, duration_seconds, resolution).
  4. Create with create_manual_video: model, prompt, and the validated duration_seconds/resolution/aspect_ratio.
    • The operation is inferred from inputs: add image_url (public https) for image-to-video. Don't pass an operation field — it doesn't exist.
  5. Wait with wait_for_video; return video_url when completed.

Rules

  • Manual mode has no avatar/voice/brand-kit — those are auto-mode only.
  • image_url must be a public https URL. If the user has a local file, upload it first (POST /v1/uploads → use the returned public_url).
  • On 400 invalid_request, fix the field named in details and retry — do not keep sending the same invalid value.
  • Follow generate-video-from-prompt for wait/result/error mechanics.
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. 2mo ago First seen · 27 lines · 57 tokens per session scan A f9a1681b15ab

Subscribe to this mod's changes

create-manual-video is a skill published in the GitHub repository egocen-vivideo/vivideo-toolchain (0 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 483 once invoked, about $0.0002 per session on Opus 5.5. 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.

Creative and media
Related

create-manual-video compared with skills from other repositories

create-manual-video next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
create-manual-videoegocen-vivideo/vivideo-toolchainSkill03mo agoMITA57Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill315k5d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code