promo-video-pipeline

promo-video-pipeline is a skill for Claude Code, Codex from rexleimo/aios. It costs 92 tokens per session (3,056 once invoked), scanned A, original, MIT.

A workflow for producing promotional videos with Remotion, a React-based tool that renders video from code. It splits a storyboard into scenes, assigns work to separate agents, combines the results, and checks the actual rendered video.

In plain words
What is it for?
Use it to build a vertical promo video from a scene timeline, coordinate parallel scene work, keep shared video components consistent, create subtitles for narration, and render the final composition.
Why use it?
It prevents scene work from drifting away from the approved storyboard, shared components, or the evidence supporting each visual claim. Rendering provides a concrete check that the finished video was produced rather than only described in code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex; mentions OpenCode.

Good fit Use it to build a vertical promo video from a scene timeline, coordinate parallel scene work, keep shared video components consistent, create subtitles for narration, and render the final composition.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rexleimo/aios/promo-video-pipeline
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 rexleimo/aios --skill promo-video-pipeline
Clone the repo
git clone --depth 1 https://github.com/rexleimo/aios

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 promo-video-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/rexleimo/aios/promo-video-pipeline/github.svg)](https://agentmods.dev/skills/rexleimo/aios/promo-video-pipeline)
Your own site
<a href="https://agentmods.dev/skills/rexleimo/aios/promo-video-pipeline"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/promo-video-pipeline/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 promo-video-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/rexleimo/aios/promo-video-pipeline"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/promo-video-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,056 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 $0.00092 $0.03056
Opus 5.5 $0.00037 $0.01222
Sonnet 5.5 $0.00018 $0.00611
Haiku 4.5 $0.00009 $0.00306

Measured 2d ago against content hash 9275b0242ad4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

promo-video-pipeline 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 2d 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.

skill-sources/promo-video-pipeline/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Promo Video Pipeline

在 video/ 这个 Remotion 子应用里产宣传片:分镜拆成独立工作项 → 并行派发子代理 → 主线程合并 → 以真实渲染产物作为完成门。命令面以 video/scripts/render.mjs 与 video/package.json 为准,本文件不发明参数。

1. 前置输入(先声明,再开工)

  • 分镜脚本 + 证据合同:video/README.md 的分镜表(帧区间、画面、字幕)与「画面主张与代码证据」表 (每条主张 → file:line)。派发前以它为准;改画面不改证据表等于交付假主张。
  • 场景清单:video/src/timeline.json 的 scenes[].id / label / frames / captions;当前 8 个场景 (hook crash resume route work team proof cta)、1355 帧、30fps(45.2 秒)、1080x1920 竖版、compositionId 为 AiosPromo。
  • 时长与台词唯一真源:video/src/timeline.ts 与 video/scripts/render.mjs 读同一份 json,帧区间只在 timeline.ts 累加;字幕只写在 json 里,由 PromoVideo.tsx 注入场景。其他文件不得硬编码帧数或自带 cues。
  • 片长由旁白决定:json 里的字幕同时是配音稿(npm run srt 导出 SRT 给剪映「文本朗读」),所以每一拍的 frames / fps 必须 ≥ 该拍字幕朗读所需秒数(估算器 video/scripts/narration.mjs,4.5 字/秒 + 每句 0.12s 换气)。 npm test 的「每拍窗口放得下该拍的旁白」会在砍帧数或加文案时先红 —— 那是硬门禁,不是建议。
  • 冻结点:webpack 入口 video/src/index.ts(render.mjs 的 ENTRY,只做 registerRoot)、场景注册表 SCENE_BY_ID(在 video/src/PromoVideo.tsx)、场景入参契约 SceneProps(video/src/timeline.ts)、 共享 primitive video/src/components/**(stage panel terminal text diagram ide)与 video/src/theme.ts(竖版 layout / size 令牌)由主线程先写定,之后转为只读。
  • 入口或共享 primitive 尚未落盘时:主线程自己先写,不派发;否则多个子代理会同时改同一批文件。

2. 独立性判定(派发之前必须成立)

  • 每个工作项只有一个文件 owner。
  • 共享 video/src/components/** 的场景不独立:主线程先冻结共享 primitive,之后每个子代理只允许新建或编辑自己的 video/src/scenes/<id>.tsx。
  • video/src/PromoVideo.tsx 的 SCENE_BY_ID 注册表与 video/src/index.ts 由主线程独占改写,子代理不碰入口与注册表。
  • timeline.json 对子代理只读;要改帧数就回报主线程,由主线程改 json 并重跑 npm test。
  • 以上任一不成立 → 保持串行,不进入派发。

3. 计划与派发(沿用 aios-work-dispatch 约定)

aios plan start --title "<宣传片目标>" --task "<整片目标>"
aios plan task hook --target video/src/scenes/hook.tsx --allow-write "video/src/scenes/hook.tsx"
aios plan task cta --target video/src/scenes/cta.tsx --allow-write "video/src/scenes/cta.tsx"
aios work --task "<宣传片目标>" --dry-run --json
  • 先建结构化 plan,让引擎拿到真实 owner 与依赖;再从 dry-run 预览核对工作项、依赖、路径冲突、merge gate。
  • 每个节点带 recipe header:tools 白名单(写场景 = edit;只做分镜/取证 = read-only)、model + 显式 task-type(场景绘制声明 frontend,程序不从自由文本反推类型)、max_turns、output_schema。
  • output_schema 是下游触发条件:schema 校验不过的产物不回传下游,只作为结构化反馈回到本节点。
  • 完整 header 与结果 schema 见 references/dispatch-contract.md。
  • 预览不授权执行:见第 4 节。

Read the full file on GitHub · 111 lines

Files

What ships with it

2 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.

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. 2d ago First seen · 111 lines · 92 tokens per session scan A 9275b0242ad4

Subscribe to this mod's changes

promo-video-pipeline is a skill published in the GitHub repository rexleimo/aios (54 stars, last pushed today), licensed MIT. It adds 92 tokens to every session and 3,056 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 2026-10-14.