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 birdilsss-byte/ai-creative-subagent-framework --skill ai-creative-subagent-frameworkgit clone --depth 1 https://github.com/birdilsss-byte/ai-creative-subagent-frameworkWrote 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/birdilsss-byte/ai-creative-subagent-framework/ai-creative-subagent-framework)<a href="https://agentmods.dev/skills/birdilsss-byte/ai-creative-subagent-framework/ai-creative-subagent-framework"><img src="https://agentmods.dev/badge/skills/birdilsss-byte/ai-creative-subagent-framework/ai-creative-subagent-framework.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00228 | $0.02653 |
| Opus 5 | $0.00114 | $0.01326 |
| Sonnet 5 | $0.00046 | $0.00531 |
| Haiku 4.5 | $0.00023 | $0.00265 |
Grade A, and why
ai-creative-subagent-framework 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 6d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 创意影视制作 — 子Agent调度框架
概览
本 Skill 将 AI 驱动的创意影视制作流程标准化为5 个专业角色 + 4 阶段工作流。适用场景:
- AI 拆解脚本 → 将原始脚本分解为可执行分镜头
- 调度创意团队 → 导演 → 美术指导 + 摄影指导 → 品牌审核 → AI 执行
- 生图生视频 → 生成 AI 图像/视频提示词、技术评估、质量把控
所有角色提示词模板在 references/ 目录,主文件只保留调度框架。
角色层级与汇报关系
总导演(用户 / 项目负责人)
│
├── 导演子agent(Script Director)
│ ├── 职责:脚本分解、创意构思、分镜脚本、团队协调
│ ├── 汇报:向总导演汇报
│ ├── 管理:美术指导、摄影指导
│ └── 协作:与品牌总监平级、与AI艺术家协作
│
│ ├── 美术指导(Art Director)
│ │ ├── 职责:场景设计、影调方案、视觉参考
│ │ └── 汇报:向导演子agent汇报
│ │
│ └── 摄影指导(Director of Photography)
│ ├── 职责:运镜设计、构图、布光
│ └── 汇报:向导演子agent汇报
│
├── 品牌总监(Brand Director)
│ ├── 职责:品牌策略、合规审核、内容审核
│ └── 汇报:向总导演汇报(与导演平级)
│
└── AI艺术家(AI Artist)
├── 职责:技术可行性评估、提示词撰写、质量把控
└── 汇报:向总导演汇报
标准 4 阶段工作流
阶段 1:创意构思(导演主导)
总导演 → 调用导演子agent → 完成分镜脚本、创意概念
│
├── 导演调用 → 美术指导(设计视觉场景)
└── 导演调用 → 摄影指导(设计运镜方案)
阶段 2:视觉设计(美术 + 摄影并行)
导演分镜脚本
│
├── 美术指导 → 场景视觉描述、影调方案、Mood Board
└── 摄影指导 → 运镜设计、构图方案、布光设计
│
└── 向导演汇报 → 导演审核确认
阶段 3:审核确认(品牌 + AI 并行)
导演 + 美术 + 摄影方案
│
├── 品牌总监 → 品牌策略审核、合规性检查、视觉审核
└── AI艺术家 → 技术可行性评估、提示词优化、质量评估
│
└── 向总导演汇报
阶段 4:终审执行(总导演决策)
所有方案 + 审核意见
│
总导演综合判断 → 终审定稿 → 输出最终方案
│
└── AI艺术家进入执行阶段 → 实际生图/生视频
快速调用模板(5 个角色)
调用导演子agent
Agent(
description="导演角色",
prompt=f"""从 references/director-agent.md 读取完整提示词
## 当前任务
{TASK_DESCRIPTION}
## 项目上下文
- 项目名称:[PROJECT_NAME]
- 项目类型:[PROJECT_TYPE]
- 品牌/产品:[BRAND_NAME] / [PRODUCT_NAME]
- 行业:[INDUSTRY_VERTICAL]
- 时长:[VIDEO_DURATION]
- 核心创意:[CREATIVE_METAPHOR]
- 叙事结构:[NARRATIVE_STRUCTURE]""",
subagent_type="claude"
)
调用美术指导
Agent(
description="美术指导角色",
prompt=f"""从 references/art-director-agent.md 读取完整提示词
## 当前任务
{TASK_DESCRIPTION}
## 项目上下文
- 基于导演分镜:[ATTACH_DIRECTOR_OUTPUT]
- 品牌调性:[BRAND_TONE]
- 色彩方案:[COLOR_PALETTE]
- 行业:[INDUSTRY_VERTICAL]""",
subagent_type="claude"
)
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.
- 6d ago First seen · 299 lines · 228 tokens per session scan A 842a3a0240cc
ai-creative-subagent-framework is a skill published in the GitHub repository birdilsss-byte/ai-creative-subagent-framework (2 stars, last pushed 2mo ago), licensed MIT. It adds 228 tokens to every session and 2,653 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
auto-video
Run and validate AutoVideo-Agent Markdown-to-video workflows, including the v0.1-compatible deterministic offline command and v0.2 provider mode with ComfyUI media, Mock or Command TTS, scene-level SRT, normalized timelines, FFmpeg, and deterministic QA. Use for build, plan, provider, or QA requests; MiniMax, hosted…
muapi-seedance-2
Expert Cinema Director skill for Seedance 2.0 (ByteDance) — high-fidelity video generation across Chinese, Global, and VIP tiers. Supports text-to-video, image-to-video, first-last-frame, omni reference, character training, omni-reference training, video editing, and watermark removal.
muapi-workflow
Build, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.
muapi-media-generation
Generate AI images, videos, music, and audio from the terminal via muapi.ai — supports 100+ models including Flux, Midjourney v7, Kling 3.0, Veo3, and Suno V5.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…