Deep Code CLI is a terminal-based AI coding assistant optimized for the DeepSeek V4 model, with controls for reasoning depth and support for extensible agent skills. Developers use it to work with code from any project directory. The catalogue skills extend its capabilities.
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 lessweb/deepcode-cli --skill video-generatorgit clone --depth 1 https://github.com/lessweb/deepcode-cliWrote 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/lessweb/deepcode-cli/video-generator)<a href="https://agentmods.dev/skills/lessweb/deepcode-cli/video-generator"><img src="https://agentmods.dev/badge/skills/lessweb/deepcode-cli/video-generator/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/lessweb/deepcode-cli/video-generator"><img src="https://agentmods.dev/badge/skills/lessweb/deepcode-cli/video-generator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00072 | $0.01584 |
| Opus 5 | $0.00036 | $0.00792 |
| Sonnet 5 | $0.00014 | $0.00317 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade A, and why
video-generator 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 today.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Generator
由 MiniMax H3 驱动，同步生成画面、对白与环境音。使用本技能目录中的 scripts/video_generator.py；需要 Python 3.10+，依赖安装命令为 python3 -m pip install -r scripts/requirements.txt。
所有用户可见说明、问题和选项使用用户的语言。
收集需求
- 整理用户的真实需求为提示词，保留主体、动作、镜头、风格、时间变化、对白内容和语言、环境音及限制条件。不要擅自添加会改变意图的设定。
- 收集用户提到的本地文件路径或 HTTP(S) 素材直链，并确定每份素材的用途。网页链接不等于素材直链；含义不清时询问。
- 支持纯文本、首尾帧、参考素材三种输入。首帧可附加尾帧；不接受只有尾帧。首尾帧仅支持 JPG/JPEG、PNG、WEBP，每张不超过 10MB，宽和高均至少 300 像素。
- 参考素材最多为 4 张图片 + 1 个视频 + 2 个音频，每个文件不超过上传接口的 50 MiB 限制。首尾帧与任何参考素材互斥；冲突时让用户选择用途，不能静默丢弃素材。
- 时长为 5–20 整数秒；未指定时采用 5 秒并在提交确认中展示。模式为
turbo（快速，缩短渲染时间）或base（质量，提升画质，模型侧每秒增加 1 积分）；默认快速。平台积分有换算，最终费用只能引用试算接口的credits。
确认比例和分辨率
用户已明确指定支持的比例或分辨率时直接采用。如果任一项缺失，必须用 AskUserQuestion 让用户选择并确认；两项都缺失时一起提问，不得默默采用默认值。
比例选项必须同时包含方向符号和文字：▭ 21:9（超宽横屏）、▭ 16:9（横屏）、▭ 4:3（横屏）、□ 1:1（正方形）、▯ 3:4（竖屏）、▯ 9:16（竖屏）。还支持 auto（自动比例，方向由模型决定），仅在用户明确选择自动时使用。若工具限制选项数量，展示最相关的几个，在题目中列出其余比例及方向供用户填写。分辨率选项为 720p、1080p。
如果宿主agent没有名为 AskUserQuestion 的工具，使用宿主agent等价的交互提问工具；没有等价工具时直接提问并等待明确回复。缺失的选择和生成授权不能通过默认选项或等待超时代替。
试算与提交确认
在技能目录运行（将占位符替换为真实参数，使用正确的 shell 引号）：
python3 scripts/video_generator.py cost \
--prompt '<最终视频提示词>' --ratio '16:9' --resolution 720p \
--duration 5 --tier turbo
素材参数同样传给 cost 和 generate：
- 首尾帧：
--first-frame '<路径或URL>'，可附加--last-frame '<路径或URL>'。 - 参考素材：重复
--image '<路径或URL>'（最多 4 次），--video '<路径或URL>'（最多 1 次），重复--audio '<路径或URL>'（最多 2 次）。
cost 校验本地素材的大小和扩展名、线上 URL 格式并调用 GET /plugin/calc-video-gen-cost，只输出 credits 和 minMinutes 等公开信息，不上传或提交任务。保存本次提示词、素材顺序和所有参数。
取得试算结果后，必须用 AskUserQuestion 询问是否提交并生成视频。问题中展示最终需求、素材用途、比例、分辨率、时长、模式、准确积分及“至少需要 minMinutes 分钟，实际可能更久”，提供“确认生成”和“取消”选项。只有用户明确确认才执行：
python3 scripts/video_generator.py generate \
--prompt '<与试算相同的提示词>' --ratio '16:9' --resolution 720p \
--duration 5 --tier turbo \
--confirmed-credits '<用户确认的credits>' \
--output "<目标 MP4 路径>"
原样复用试算参数及素材。不要直接调用上游API接口，也不要绕过脚本的确认参数。 核价变化时不会上传或提交，应重新试算并再次让用户确认。需求或素材发生变化也需重新试算、确认。
What ships with it
2 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.
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.
- today First seen · 78 lines · 72 tokens per session scan A 5a6d37e934f9
video-generator is a skill published in the GitHub repository lessweb/deepcode-cli (2,233 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,584 once invoked, about $0.0004 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 2026-09-10.
Other skills, from other repositories
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
imagegen
Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.
codex-router-media
Generate video, music, speech, or images with the operator's MiniMax Token Plan subscription through the codex-router media CLI. Use when the session runs a MiniMax custom (non-OpenAI) model (for example minimax-m3) with the MiniMax Token Plan provider connected, and the user explicitly asks to create a video, a song…
shortfilm-prompt
A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.
ppt-designer
A guide for planning and designing PowerPoint presentations. It covers slide structure, layouts, visual choices, animation suggestions, and speaker notes.
image-compress
A local tool for shrinking images, changing their dimensions, and converting between JPG, PNG, and WebP formats. It can process one image or all matching images in a folder.