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 bozhouDev/video-skills-toolkit --skill hyperframes-scene-animatorgit clone --depth 1 https://github.com/bozhouDev/video-skills-toolkitWrote 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/bozhoudev/video-skills-toolkit/hyperframes-scene-animator)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00125 | $0.03092 |
| Opus 5 | $0.00063 | $0.01546 |
| Sonnet 5 | $0.00025 | $0.00618 |
| Haiku 4.5 | $0.00013 | $0.00309 |
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.
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:
- 项目的 manifest 与 template handoff;
- 已锁定的导演脚本、制作规格、素材计划、对齐字幕和 motion contract;
- 本地 AESTHETICS.md;
- 本地 runtime adaptation contract;
- 当前启用的
hyperframes、hyperframes-core、hyperframes-animation与hyperframes-cliskills。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 的 .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
- 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。
- 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。 - 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。
- 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。
- 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: worker、fork_turns: none、model: gpt-5.4-mini、reasoning_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。
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.
- AESTHETICS.md 6.1 KB
- agents/openai.yaml 430 B
- assets/review-templates/executor-report.md 1.5 KB
- assets/review-templates/lead-review.md 963 B
- assets/review-templates/proof-manifest-v1.template.json 1.5 KB
- evals/evals.json 8.9 KB
- evals/fixtures/contracts/DESIGN.md 118 B
- evals/fixtures/contracts/invalid-missing-acceptance-mapping.json 175 B
- evals/fixtures/contracts/invalid-missing-beat-mapping.json 145 B
- evals/fixtures/contracts/invalid-readable-hold-motion.json 283 B
- evals/fixtures/contracts/valid-hyperframes.json 3.6 KB
- evals/fixtures/contracts/valid-legacy-remotion.json 5.3 KB
- evals/fixtures/contracts/valid-runtime-adaptation.json 7.7 KB
- evals/fixtures/contracts/valid-runtime-content.html 2.1 KB
- evals/fixtures/hyperframes-motion-regression.html 2.7 KB
- evals/fixtures/ready-project/.npmrc 20 B
- evals/fixtures/ready-project/assets/audio/voice/voice.mp3 80 KB
- evals/fixtures/ready-project/assets/fonts/NotoSansSC-400.ttf 10294 KB
- evals/fixtures/ready-project/assets/fonts/NotoSansSC-500.ttf 10287 KB
- evals/fixtures/ready-project/assets/fonts/NotoSansSC-700.ttf 10284 KB
- evals/fixtures/ready-project/assets/fonts/SpaceGrotesk-400.ttf 68 KB
- evals/fixtures/ready-project/caption-overrides.json 3 B
- evals/fixtures/ready-project/compositions/caption-overlay.html 3.0 KB
- evals/fixtures/ready-project/compositions/content.html 10 KB
- evals/fixtures/ready-project/compositions/pip-overlay.html 2.4 KB
- evals/fixtures/ready-project/compositions/studio-background.html 7.6 KB
- evals/fixtures/ready-project/DESIGN.md 5.6 KB
- evals/fixtures/ready-project/hyperframes.json 318 B
- evals/fixtures/ready-project/index.html 1.7 KB
- evals/fixtures/ready-project/inputs/captions/captions_aligned.json 290 B
- evals/fixtures/ready-project/inputs/motion-contract.json 5.8 KB
- evals/fixtures/ready-project/inputs/制作规格.md 300 B
- evals/fixtures/ready-project/inputs/视频脚本.md 243 B
- evals/fixtures/ready-project/inputs/素材计划.md 233 B
- evals/fixtures/ready-project/manifest.json 4.4 KB
- evals/fixtures/ready-project/meta.json 191 B
- evals/fixtures/ready-project/package.json 2.9 KB
- evals/fixtures/ready-project/proof/goldens/narrow-center-grid-t000.png 327 KB
- evals/fixtures/ready-project/proof/goldens/narrow-center-grid-t004.png 336 KB
- evals/fixtures/ready-project/proof/goldens/narrow-center-grid-t009.png 334 KB
- evals/fixtures/ready-project/renders/internal-preview-v1.mp4 1305 KB
- evals/fixtures/ready-project/renders/preview-v1.mp4 1305 KB
- evals/fixtures/ready-project/review/animation-map-v1/animation-map.json 39 KB
- evals/fixtures/ready-project/review/approval-receipt-v1.json 544 B
- evals/fixtures/ready-project/review/cli/animation-map.txt 2.0 KB
- evals/fixtures/ready-project/review/cli/check.txt 3.3 KB
- evals/fixtures/ready-project/review/cli/contact-sheet.txt 87 B
- evals/fixtures/ready-project/review/cli/doctor.txt 1.3 KB
- evals/fixtures/ready-project/review/cli/fixed-stage.txt 174 B
- evals/fixtures/ready-project/review/cli/inputs.txt 164 B
- evals/fixtures/ready-project/review/cli/inspect.txt 244 B
- evals/fixtures/ready-project/review/cli/lint.txt 62 B
- evals/fixtures/ready-project/review/cli/media.txt 78 B
- evals/fixtures/ready-project/review/cli/motion-contract.txt 191 B
- evals/fixtures/ready-project/review/cli/render.txt 11 KB
- evals/fixtures/ready-project/review/cli/runtime-adaptation.txt 204 B
- evals/fixtures/ready-project/review/cli/snapshot.txt 1.2 KB
- evals/fixtures/ready-project/review/cli/stage.txt 58 B
- evals/fixtures/ready-project/review/cli/validate.txt 216 B
- evals/fixtures/ready-project/review/execution-handoff.md 734 B
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.
- 8d ago First seen · 71 lines · 125 tokens per session scan A a6541d3ab481
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.
Other skills, from other repositories
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
video-hyperframes
A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.
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…
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…
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.
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.