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 aAAaqwq/AGI-Super-Team --skill aigc-directorgit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/aigc-director)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/aigc-director"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/aigc-director/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.
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/aigc-director"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/aigc-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, 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 100 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.
- high Privilege Escalation · line 118 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.
- high Privilege Escalation · line 119 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 | $0.00102 | $0.03484 |
| Opus 5 | $0.00051 | $0.01742 |
| Sonnet 5 | $0.00020 | $0.00697 |
| Haiku 4.5 | $0.00010 | $0.00348 |
Grade A, and why
aigc-director scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "http://localhost:8000/api/project/{session_id}/artifact/{stage}" How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIGC-Director Agent Skill
本地运行：这是一个本地部署的视频生成项目，前后端都运行在本机：
- 后端：
http://localhost:8000- 前端：
http://localhost:3000- 所有 API 调用都请求本地服务器，不要请求其他地址！
- 确保在调用任何 API 之前，后端和前端服务都已经启动并运行正常！
核心理念：Agent 应该像"持续陪伴的智能视频制作助理"，每完成一个用户可感知的重要任务，都应立即给用户一条简报，并等待用户确认。
核心原则：每个阶段的产物都必须展示给用户，必须停下来等待用户确认后才能继续下一阶段。
防止遗忘：在整个流程中，Agent 可能会忘记之前的用户输入或之前阶段的产物内容。每当进入一个新的阶段时，Agent 都必须重新加载这篇SKILL文档，确保不会忘记任何细节。
项目结构
aigc-director/ ← OpenClaw 调用的 skill 根目录
├── aigc-claw/ ← 前后端项目代码
│ ├── backend/ ← FastAPI 后端（端口 8000）
│ │ └── code/result/ ← 模型生成产物存放目录
│ │ ├── script/ ← 剧本产物
│ │ ├── image/ ← 图片产物（角色、场景、参考图）
│ │ └── video/ ← 视频产物
│ └── frontend/ ← Next.js 前端（端口 3000）
├── references/ ← OpenClaw 调用时的参考文档
│ ├── init_project/ ← 项目初始化
│ ├── run_project/ ← 服务启动
│ ├── workflow/ ← 六阶段工作流 API
│ ├── sandbox/ ← 临时工作台 API
│ └── send_message/ ← 消息发送
└── SKILL.md ← skill 正文
产物存放目录：
aigc-claw/backend/code/result/
script/- 剧本产物image/- 图片产物（角色、场景、参考图）video/- 视频产物
阶段与停点（共9个）
| 停点 | 阶段 | phase 值 | 描述 | 操作 |
|---|---|---|---|---|
| 1 | 项目配置 | - | 确认配置选项 | 展示配置 → 用户确认 |
| 2 | 剧本生成 | suggest_expand | 建议扩写 | 等待用户确认 |
| 3 | 剧本生成 | logline_selection | 选择情节 | 从3个候选中选择 |
| 4 | 剧本生成 | mode_selection | 选择模式 | 电影(4幕) / 微电影(1幕) |
| 5 | 剧本生成 | script_generation | 确认剧本 | 确认后继续 |
| 6 | 角色/场景设计 | - | 确认角色/场景图片 | 确认后继续 |
| 7 | 分镜设计 | - | 确认分镜列表 | 确认后继续 |
| 8 | 参考图生成 | - | 确认参考图 | 确认后继续 |
| 9 | 视频生成 | - | 确认视频片段 | 确认后继续 |
注意：
suggest_expand和logline_selection可能根据输入质量被跳过。
工作流程
1. 本地部署(仅初始化时执行)
当用户要求"初始化项目"、"配置项目"、"部署项目"时，需要先进行项目初始化：参考 init_all.md 执行完整初始化流程。
注意：仅在用户首次下载项目或需要重新配置环境时使用。项目已初始化过则跳过此步骤，直接检查服务运行状态。
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.
- .gitignore 295 B
- aigc-claw/backend/__init__.py 69 B runs code
- aigc-claw/backend/.gitignore 71 B
- aigc-claw/backend/api_server.py 44 KB runs code
- aigc-claw/backend/config_model.json 7.8 KB
- aigc-claw/backend/config_model.py 1.6 KB runs code
- aigc-claw/backend/config.py 3.8 KB runs code
- aigc-claw/backend/core/__init__.py 127 B runs code
- aigc-claw/backend/core/agents/__init__.py 541 B runs code
- aigc-claw/backend/core/agents/base_agent.py 1.7 KB runs code
- aigc-claw/backend/core/agents/character_agent.py 27 KB runs code
- aigc-claw/backend/core/agents/editor_agent.py 2.7 KB runs code
- aigc-claw/backend/core/agents/reference_agent.py 31 KB runs code
- aigc-claw/backend/core/agents/script_agent.py 68 KB runs code
- aigc-claw/backend/core/agents/storyboard_agent.py 17 KB runs code
- aigc-claw/backend/core/agents/video_agent.py 27 KB runs code
- aigc-claw/backend/core/orchestrator.py 23 KB runs code
- aigc-claw/backend/docs/api.md 9.9 KB
- aigc-claw/backend/docs/session_format.md 6.3 KB
- aigc-claw/backend/prompts/character/character_styles.txt 9.5 KB
- aigc-claw/backend/prompts/character/character_zh.txt 647 B
- aigc-claw/backend/prompts/character/eval_character_zh.txt 1.8 KB
- aigc-claw/backend/prompts/character/eval_select_best_zh.txt 1.5 KB
- aigc-claw/backend/prompts/loader.py 4.8 KB runs code
- aigc-claw/backend/prompts/logline/check_en.txt 190 B
- aigc-claw/backend/prompts/logline/check_zh.txt 268 B
- aigc-claw/backend/prompts/logline/extract_zh.txt 413 B
- aigc-claw/backend/prompts/logline/generate_en.txt 508 B
- aigc-claw/backend/prompts/logline/generate_zh.txt 671 B
- aigc-claw/backend/prompts/reference/eval_first_frame_zh.txt 2.4 KB
- aigc-claw/backend/prompts/reference/eval_select_best_zh.txt 1.7 KB
- aigc-claw/backend/prompts/reference/first_frame_en.txt 624 B
- aigc-claw/backend/prompts/reference/first_frame_zh.txt 600 B
- aigc-claw/backend/prompts/script/beat_sheet_en.txt 817 B
- aigc-claw/backend/prompts/script/beat_sheet_zh.txt 863 B
- aigc-claw/backend/prompts/script/micro_beat_sheet_en.txt 500 B
- aigc-claw/backend/prompts/script/micro_beat_sheet_zh.txt 490 B
- aigc-claw/backend/prompts/script/micro_step_outline_zh.txt 1.2 KB
- aigc-claw/backend/prompts/script/step_outline_en.txt 1.2 KB
- aigc-claw/backend/prompts/script/step_outline_zh.txt 1.2 KB
- aigc-claw/backend/prompts/script/validate_characters_zh.txt 1.1 KB
- aigc-claw/backend/prompts/script/validate_settings_zh.txt 859 B
- aigc-claw/backend/prompts/setting/eval_select_best_zh.txt 1.4 KB
- aigc-claw/backend/prompts/setting/eval_setting_zh.txt 1.6 KB
- aigc-claw/backend/prompts/setting/setting_styles.txt 5.2 KB
- aigc-claw/backend/prompts/setting/setting_zh.txt 212 B
- aigc-claw/backend/prompts/storyboard/continue_zh.txt 1.6 KB
- aigc-claw/backend/prompts/storyboard/shot_zh.txt 1.2 KB
- aigc-claw/backend/prompts/video/enhance.txt 1.5 KB
- aigc-claw/backend/requirements.txt 361 B
- aigc-claw/backend/session.py 2.2 KB runs code
- aigc-claw/backend/tool/image_client.py 9.1 KB runs code
- aigc-claw/backend/tool/image_dashscope.py 7.0 KB runs code
- aigc-claw/backend/tool/image_gpt.py 10 KB runs code
- aigc-claw/backend/tool/image_jimeng.py 16 KB runs code
- aigc-claw/backend/tool/image_processor.py 16 KB runs code
- aigc-claw/backend/tool/image_seedream.py 9.9 KB runs code
- aigc-claw/backend/tool/llm_client.py 5.7 KB runs code
- aigc-claw/backend/tool/llm_dashscope.py 4.5 KB runs code
- aigc-claw/backend/tool/llm_deepseek.py 3.3 KB runs code
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.
- 11d ago First seen · 280 lines · 102 tokens per session scan A 7c23c11a339d
aigc-director is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 3,484 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
loom-artifacts
Receive files from the CodexLoom Thread composer and publish generated images or files back to the Thread as managed artifacts. Use when a user message contains loomattachments; an attached document, data file, image, or archive must be read; or the Agent has produced a file that the user should preview or download.…
exploring-zero-resource-designs
Use when exploring zero resource designs is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
framing-creative-challenge
Use when framing creative challenge is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
mutating-idea-genomes
Use when mutating idea genomes is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
scoring-contextual-creativity
Use when scoring contextual creativity is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
using-denial-ladders
Use when using denial ladders is required during creativity work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.