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 good-boy4069/Deepseek-omnimodal --skill omnimodalgit clone --depth 1 https://github.com/good-boy4069/Deepseek-omnimodalWrote 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/good-boy4069/deepseek-omnimodal/omnimodal)<a href="https://agentmods.dev/skills/good-boy4069/deepseek-omnimodal/omnimodal"><img src="https://agentmods.dev/badge/skills/good-boy4069/deepseek-omnimodal/omnimodal/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/good-boy4069/deepseek-omnimodal/omnimodal"><img src="https://agentmods.dev/badge/skills/good-boy4069/deepseek-omnimodal/omnimodal.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 | $0.00082 | $0.01388 |
| Opus 5 | $0.00041 | $0.00694 |
| Sonnet 5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
omnimodal 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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Omnimodal
主模型使用纯文本模型时，只要任务需要看媒体、听媒体或生成媒体，就自动调用 omnimodal_* MCP 工具，不要等用户手动开启，也不要自行假设媒体内容。
自动触发
- 用户消息中有图片、视频、音频路径或附件。
- 任务包含 OCR、截图、UI、设计稿、图表、表格图片、错误弹窗、音频/视频理解。
- 主任务不是媒体任务，但为了完成它必须知道媒体内容。
- 用户要求生成图片、视频、语音、音乐、声音克隆或声音设计。
识别工具
- 单张图片：
omnimodal_recognize_image(image, task, mode)。image支持本地路径、data:URL 和可解码的 base64。 - 多张图片：
omnimodal_recognize_images_batch(images, task, mode, max_workers)。 - 单个视频：
omnimodal_recognize_video(video, task, mode)。 - 批量视频：
omnimodal_recognize_videos_batch(videos, task, mode, max_workers)。 - 单个音频：
omnimodal_recognize_audio(audio, task, mode)，长音频自动走 ASR 转写。 - 批量音频：
omnimodal_recognize_audios_batch(audios, task, mode, max_workers)。 - 剪贴板图片：
omnimodal_read_clipboard_image(task, mode)。 - 拖拽媒体：
omnimodal_read_dragged_image/omnimodal_read_dragged_video/omnimodal_read_dragged_audio。
网页动态内容先调用 omnimodal_capture_page(url, actions, viewport, output_dir)，再把截图路径交给批量识别。Windows 全屏、主屏或指定窗口截图先调用 omnimodal_list_windows()，再调用 omnimodal_capture_windows(mode, window, output_dir)。
生成工具
omnimodal_generate_image(prompt, tier, size, n, wait, confirm)：文生图。omnimodal_generate_video(prompt, tier, duration, resolution, wait, confirm)：文生视频。omnimodal_generate_video_from_image(image, prompt, tier, duration, resolution, wait, confirm)：图生视频。omnimodal_edit_video(video, prompt, tier, duration, resolution, reference_image, wait, confirm)：视频编辑。omnimodal_generate_audio(text, voice, tier, kind, preview_text, wait, confirm)：TTS、声音克隆、声音设计、音乐生成。omnimodal_get_task_result(task_id)：查询异步任务。
费用确认是强制规则：生成工具必须在调用时传 confirm=true；否则返回预计费用且不实际调用付费接口。不要绕过确认。
生成后不要自动识别验证：用户要求生成图片、视频或音频时，只调用对应生成工具并直接返回结果路径；不要为了“检查生成效果”再自动调用识别工具。只有用户明确要求检查生成结果、或生成结果明显异常时才允许追加识别。
mode 档位
识别档位统一为：
ocr：仅图片文字提取。quick：快速识别，关闭思考，短输出。standard：标准提取，默认。full：完整提取，不限制输出。quick_analysis/balanced_analysis/deep_analysis：逐步加强的分析档。
档位可通过插件目录 config/profiles.json 覆盖；本机私有覆盖写在 config/local.json，不会进入 Git。
What ships with it
1 file 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.
- 11d ago First seen · 89 lines · 82 tokens per session scan A 91915ccdedd0
omnimodal is a skill published in the GitHub repository good-boy4069/Deepseek-omnimodal (4 stars, last pushed 25d ago), licensed MIT. It adds 82 tokens to every session and 1,388 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 2026-08-31.
Other skills, from other repositories
watching-videos
The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's in this recording". Use this to actually watch the video — download, extract frames, OCR, transcribe, and index it …
extracting-structure
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is my intro/hook". Use this for deterministic extraction from the index — chapters with timestamps, a fileable bug report…
glmv-pdf-to-ppt
Convert a PDF (research paper, report, or any document) into a polished multi-slide HTML presentation with a structured outline JSON and summary markdown. Trigger this skill when the user mentions making slides or a PPT from a PDF — in Chinese or English.
glmv-caption
Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the content of images, videos, or files. Supports single/multiple inputs, URLs, local paths, and base64 (images only).
glmv-prompt-gen
Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to generate prompts from reference images/videos, create AI art prompts, or get prompt engineering suggestions from visual…
vision-skills
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/htmlshot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long…