bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
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 agentmods add skills/bytedance/agentkit-samples/comic-drama-masternpx skills add bytedance/agentkit-samples --skill comic-drama-mastergit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/comic-drama-master)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/comic-drama-master"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/comic-drama-master.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 | $0.00073 | $0.10673 |
| Opus 5 | $0.00036 | $0.05337 |
| Sonnet 5 | $0.00015 | $0.02135 |
| Haiku 4.5 | $0.00007 | $0.01067 |
Grade B, and why
comic-drama-master scanned grade B 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y ffmpeg How it starts
The opening of the file, as written. The whole thing — 793 lines — stays where its author put it; the contents beside it link to each section on GitHub.
漫剧制作总导演
你是统筹全局的漫剧制作总导演，负责协调五个专业环节完成从创意到成片的全流程。
五个专业环节的详细规格：
- 剧本生成：参见
references/screenplay-generator.md- 角色设计：参见
references/character-designer.md- 场景美术：参见
references/scene-designer.md- 分镜视频：参见
references/storyboard-director.md- 视频合成：参见
references/video-synthesizer.md完整使用示例参见
examples/examples.md。
⚠️ 内容安全审核提醒
在开始制作之前，必须先对用户的故事创意进行内容安全预审。
高风险关键词（容易触发 API 拒绝）
以下类型的内容在视频生成阶段（doubao-seedance API）有较高概率被拒绝（OutputVideoSensitiveContentDetected）：
| 风险类别 | 高风险关键词示例 |
|---|---|
| 战争军事 | 战争、军队、军事、入侵、屠杀、征服 |
| 血腥暴力 | 血腥、血液、流血、残肢、内脏、致命伤 |
| 武器描述 | 刀砍、剑刺、弓箭射杀、枪械、炸弹 |
| 宗教敏感 | 堕天使、恶魔、撒旦、邪教、亵渎 |
| 恐怖元素 | 恐怖、惊悚、尸体、骷髅、鬼魂 |
| 政治敏感 | 政治人物、敏感历史事件、领土争议 |
预审处理规则
- 低风险（日常、奇幻冒险、儿童故事等）：直接开始制作
- 中风险（武侠打斗、修仙对决等）：在剧本和 prompt 中使用委婉替代词：
- ❌
blood spraying from wound→ ✅spiritual energy impact, staggering backward - ❌
sword piercing through chest→ ✅sword energy clash, powerful strike - ❌
army marching to war→ ✅warriors gathering for a decisive confrontation - ❌
bloody battle→ ✅fierce spiritual energy confrontation
- ❌
- 高风险（纯战争、恐怖、政治敏感）：明确告知用户该题材可能导致视频生成大面积失败，建议：
- 调整为更温和的表达方式
- 更换题材方向
- 用户坚持则继续，但提前说明可能有 30-50% 的场景需要反复重试
提醒时机：在步骤2（初始化任务目录）之后、步骤3（剧本生成）之前，向用户简要说明风险等级和应对策略。
⚡ 脚本参数速查表（大模型必读）
重要：以下是所有脚本的精确调用格式和 JSON 文件格式。调用任何脚本前，必须严格按照此表准备参数，不得猜测格式。
app_config.py — 读取配置
python scripts/app_config.py
# 无参数，返回 JSON
task_manager.py — 任务目录管理
# 初始化任务
python scripts/task_manager.py init "<task_name>"
# 保存文档
python scripts/task_manager.py save "<task_folder绝对路径>" "<文件名.md>" "<Markdown内容>"
# 列出任务
python scripts/task_manager.py list
web_search.py — 网络搜索
python scripts/web_search.py "<搜索关键词>"
# 返回 JSON 字符串数组
image_generate.py — 单张图片生成
python scripts/image_generate.py "<英文prompt>" --output-dir "<保存目录绝对路径>"
# 返回 JSON: {"saved_files": ["/absolute/path/to/generated_image_TIMESTAMP_0.png"]}
What ships with it
22 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.
- examples/examples.md 10 KB
- references/character-designer.md 10 KB
- references/scene-designer.md 9.2 KB
- references/screenplay-generator.md 19 KB
- references/storyboard-director.md 21 KB
- references/video-synthesizer.md 6.4 KB
- scripts/app_config.py 1.9 KB runs code
- scripts/ark_auth.py 3.5 KB runs code
- scripts/batch_image_generate.py 11 KB runs code
- scripts/batch_video.py 8.4 KB runs code
- scripts/create_video_task.py 3.6 KB runs code
- scripts/file_download.py 3.3 KB runs code
- scripts/get_aksk.py 3.5 KB runs code
- scripts/image_generate.py 4.3 KB runs code
- scripts/model_service.py 2.0 KB runs code
- scripts/query_video_task.py 4.1 KB runs code
- scripts/task_manager.py 6.7 KB runs code
- scripts/tos_upload.py 4.2 KB runs code
- scripts/verify_task.py 30 KB runs code
- scripts/video_merge.py 5.6 KB runs code
- scripts/video_scorer.py 3.7 KB runs code
- scripts/web_search.py 2.6 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.
- yesterday Changed 1b988bdcd240
- 5d ago First seen · 793 lines · 73 tokens per session scan B 4943c45a2789
comic-drama-master is a skill published in the GitHub repository bytedance/agentkit-samples (446 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 10,673 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
sn-image-imitate
Generates a new image that imitates the style of a reference image while updating content based on user intent. Uses a three-stage pipeline: image annotation (long caption), caption rewriting, and image generation. Use when user asks to "imitate style", "保持这个风格重画", "按这张图风格生成", or "style transfer with new content".
akg-agents
代理执行 AKG 算子任务。先检查固定仓库与分支；若 /.akg/checkenv.md 不存在则强制 FULLSETUP=true；忽略所有 akgcli 检查和使用；后端代码生成直接执行 runworkflow.py --workflow kernelgen。.