A workflow for creating and editing product, launch, demo, or social videos from a coding project using 21st video tools. It keeps the editable video project open while changes are made and exports the result.

It helps choose video blocks, compose short scenes, make small revisions, inspect rendered frames, offer visual variations, and export a video.

It gives the agent a way to base video content on the project's real screens, copy, brand assets, and release information instead of inventing product details.

21st-video — Skill for Codex by 21st-dev/codex-plugin

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 21st-dev/codex-plugin --skill 21st-video

Clone the repo

git clone --depth 1 https://github.com/21st-dev/codex-plugin

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/21st-dev/codex-plugin/21st-video/github.svg)](https://agentmods.dev/skills/21st-dev/codex-plugin/21st-video)

Your own site

<a href="https://agentmods.dev/skills/21st-dev/codex-plugin/21st-video"><img src="https://agentmods.dev/badge/skills/21st-dev/codex-plugin/21st-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/21st-dev/codex-plugin/21st-video"><img src="https://agentmods.dev/badge/skills/21st-dev/codex-plugin/21st-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,516 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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.01516
Opus 5.5	$0.00041	$0.00606
Sonnet 5.5	$0.00020	$0.00303
Haiku 4.5	$0.00010	$0.00152

Measured 9d ago against content hash 17bcb589f3c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

21st-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 9d 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/21st-video/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

21st Video

Create the video with the user's coding agent and the 21st video tools. Keep the real editor open so the user can see changes and edit the same project by hand. Use the available tool input schemas as the source of truth for fields, operation names, limits, and supported formats.

Start from the product

Read the project's README, relevant screens/components, brand assets, and release notes. Use real product copy and assets. Establish one message, an appropriate aspect ratio, and a short scene sequence from the user's request. Keep claims grounded in the product. Respect project instructions and any restriction on browser or computer use. Reuse the user's running app; start a server only when authorized.

Inspect the available video_* tools before starting. If they are absent, report that this connection does not offer video authoring. Use the existing 21st-cli-use skill for finding and installing React components; video blocks use the separate video catalog.

Create and open the project

Call video_list_blocks or video_search_blocks for relevant blocks. Read each chosen block's supported sizes and props schema before composing it.
Call video_create_project with a title and size (16:9, 9:16, or 1:1). Choose at most one of template (a slug), blockRef (one block with optional props), or blocks (initial kit ops); omit all for empty. Retain the returned projectId, rev, and editorUrl.
Immediately open the returned editorUrl in the host's in-app browser. In Codex, use the native browser-opening tool, such as open_in_codex with a browser URL, when available. The URL already selects Codex host mode and includes a short-lived, single-use handoff. Open it intact and promptly; never print the handoff token or persist that URL to a repo or log. For final links, remove the handoff fragment from the project's editor URL. If the host cannot open the editor, give the stable link and continue with tools.
Call video_get_doc for the actual document, current revision, and editorContext containing the user's current selection/frame/view size.

Read the full file on GitHub · 124 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.

agents/openai.yaml 223 B

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.

9d ago First seen · 124 lines · 102 tokens per session scan A 17bcb589f3c9

Subscribe to this mod's changes

21st-video is a skill published in the GitHub repository 21st-dev/codex-plugin (10 stars, last pushed 10d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,516 once invoked, about $0.0004 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 2026-10-08.

Creative and media

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens