hyperframes-scene-animator

hyperframes-scene-animator is a skill for Codex from bozhouDev/video-skills-toolkit. It costs 125 tokens per session (3,092 once invoked), scanned A, original, MIT.

A production workflow for adding subtitles, scene direction, transitions, sound cues, and motion effects to talking-head videos. It requires a completed handoff with approved files and production details before making changes.

In plain words
What is it for?
Use it to turn an approved talking-head video plan into finished animated scenes and a reviewed preview. It supports checking subtitles, timing, transitions, sound cues, and motion against the supplied production contracts.
Why use it?
It prevents animation work from starting with missing files, uncertain creative decisions, or mismatched versions. It also requires a still-page review before motion is added.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to turn an approved talking-head video plan into finished animated scenes and a reviewed preview. It supports checking subtitles, timing, transitions, sound cues, and motion against the supplied production contracts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bozhoudev/video-skills-toolkit/hyperframes-scene-animator
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 bozhouDev/video-skills-toolkit --skill hyperframes-scene-animator
Clone the repo
git clone --depth 1 https://github.com/bozhouDev/video-skills-toolkit

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.

agentmods badge for hyperframes-scene-animator

README.md
[![agentmods](https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/hyperframes-scene-animator.svg)](https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/hyperframes-scene-animator)
Your own site
<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/hyperframes-scene-animator"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/hyperframes-scene-animator.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,092 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

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 →

  • high Privilege Escalation · line 22
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00125 $0.03092
Opus 5 $0.00063 $0.01546
Sonnet 5 $0.00025 $0.00618
Haiku 4.5 $0.00013 $0.00309

Measured 8d ago against content hash a6541d3ab481, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hyperframes-scene-animator 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 8d 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/hyperframes-scene-animator/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HyperFrames Scene Animator

在固定舞台交接后,先完成全镜头最终静态页的人工审核,再制作动效并闭环至 preview-v1。固定模板仍归 talking-head-hyperframes 所有。

开工门禁

每次执行先读取:

  1. 项目的 manifest 与 template handoff;
  2. 已锁定的导演脚本、制作规格、素材计划、对齐字幕和 motion contract;
  3. 本地 AESTHETICS.md
  4. 本地 runtime adaptation contract
  5. 当前启用的 hyperframeshyperframes-corehyperframes-animationhyperframes-cli skills。只有写 GSAP 时才加载对应 adapter/GSAP reference,只有实现真实 scene boundary 时才加载 transition overview、catalog 和所选转场类别。

进入 proof 与审片阶段时再读 proof and review contract,不要在编排阶段提前加载。

首次执行任何项目 package script 前,先用本 Skill 自带的 scripts/verify_project_bundle.mjs <project-dir> 验证 factory-owned 脚本、完整 package script 集合和只含 ignore-scripts=true.npmrc;任何额外 pre/post hook、项目 Node options 或字节差异都必须停止,不能执行项目代码。通过后只使用生成项目公开的 package scripts 运行校验、proof 和 failure gates;不要复制活动 HyperFrames skills 的运行时文档,也不要依赖不可复现的隐藏手工步骤。

只有 manifest 明确为 READY_FOR_EXECUTION,且 handoff 中每个必填输入的实际路径、项目相对路径、SHA-256、媒体/字幕校验和 motion-contract source hash 都与实物一致,才可写内容 composition。

遇到 TEMPLATE_ONLY、缺失文件、无效媒体/字幕、未确认导演决定、合同缺字段/未覆盖整片或 hash 不一致时:

  • 立即拒绝执行;
  • 按项目实际状态逐项列出缺失或无效项,包含字段/期望路径、实际路径、期望 hash、实际 hash 或无法取得的原因;
  • 指明应回到 factory 还是上游锁定资料;
  • 不创建或修改任何内容 composition、场景、动效、转场或声音 cue。

不得用临时导演、占位场景或“先做几个看看”绕过门禁。

五条防回退红线

  1. 一镜头只讲一个命题。 屏幕只留口播当下需要记住的关键字;主词必须在字号、对比、位置或空间上显著压过辅助信息。不要把解释性隐喻、来源备注、英文装饰词和多组数据同时堆在画面上。
  2. 章节牌是事件,不是常驻挂件。 章节只在独立场景中出现一次,让观众读懂后结束。不得让“招牌热菜”、NO.01、章节标签或装饰卡在后续镜头中持续占位。
  3. 一个场景只有一层主空间。 禁止“外面一层页面,里面又塞一层完整背景框”的 PPT 套娃,也禁止没有口播含义的系统框、权限夹、执行工位和未解释标签。概念改变就切新场景;所有可见元素都必须服务当下命题。
  4. 先审静态定稿,再做任何动效。 依据字幕交付每个镜头信息完全呈现时的最终静态页和整片联系表。未获得用户对整套静态镜头的明确批准,不得写动效、转场或整片预览。
  5. 音频微剪以听感和音素完整性为准。 不得只依赖 silencedetect、波形或字级时间戳判断插入/删除点;停顿只放在完整语义短语边界,不得切在一个字或辅音内。每次从未修改的已批准母带按 EDL 重建,先输出 6–10 秒试听并获得人工批准,再按分段时间偏移同步下游字幕、cue、时长和 hash。本 Skill 不直接改锁定人声;修改后必须回到上游重新锁定输入。

主 Agent 与快速子 Agent

  • 主 Agent 是唯一导演、编辑与集成者:它负责字幕→beat→镜头的划分,锁定可见文字、素材、布局层级、每个镜头具体怎么写、时序、转场接力与验收标准,并审查全部合并结果。
  • 完成主 Agent 的逐镜锁定简报后,把互不冲突的镜头页/镜头模块优先分配给快速子 Agent。调用 spawn_agent 时默认使用 agent_type: workerfork_turns: nonemodel: gpt-5.4-minireasoning_effort: medium,并在自包含 prompt 中写清下面的任务合同;该模型不可用时,选当前最快且能稳定完成 HTML/SVG/GSAP 的 worker 模型。
  • 每个子 Agent 必须获得自包含的逐镜任务:字幕时段、单一命题、最终静态图、允许的文字/素材、尺寸与设计 token、入/出状态、精确文件所有权和验收帧。子 Agent 只实现,不重新规划、不增删屏幕文案、不改镜头数量、不改全局视觉/动效语言。
  • 子 Agent 只修改分配给它的独立文件;content.html、全局 timeline、shared styles/tokens、runtime adaptation、转场接力、音频/字幕及最终集成只由主 Agent 修改。场景不独立或强共享文件时,不强行并行。
  • 审查可由其他 Agent 发现问题,但修改仍回到原镜头文件所有者或主 Agent;不得创建第二套竞争实现。所有 Agent 都必须适配共享工作区已有改动,不回退他人的工作。

Read the full file on GitHub · 71 lines

Files

What ships with it

60 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. 8d ago First seen · 71 lines · 125 tokens per session scan A a6541d3ab481

Subscribe to this mod's changes

hyperframes-scene-animator is a skill published in the GitHub repository bozhouDev/video-skills-toolkit (138 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 3,092 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

video-hyperframes

Hyperframes / Remotion-compatible continuous frame animation with autoplay support.

nexu-io/open-design · 18 tokens

video-hyperframes

A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.

nexu-io/html-anything · 22 tokens

remocn

Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…

Remocn/remocn · 88 tokens

minimax-cli

Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…

Lingtai-AI/lingtai · 72 tokens

videoagent-audio-studio

Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.

pexoai/pexo-skills · 50 tokens

multimodal-llm

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.

yonatangross/orchestkit · 82 tokens