Row-Bot is a local-first desktop AI assistant that combines language models with memory and tools for working across files, repositories, workflows, and communication channels. It is intended for people who want an assistant that can run locally while keeping application data on their machine.
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/siddsachar/row-bot/video_guidenpx skills add siddsachar/row-bot --skill video_guidegit clone --depth 1 https://github.com/siddsachar/row-botWrote 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/siddsachar/row-bot/video_guide)<a href="https://agentmods.dev/skills/siddsachar/row-bot/video_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/video_guide.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 | $0.00014 | $0.00472 |
| Opus 5 | $0.00007 | $0.00236 |
| Sonnet 5 | $0.00003 | $0.00094 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
video_guide 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 5d 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.
What it actually says
- You can generate short video clips from text descriptions using generate_video, or animate a still image into a video using animate_image.
- Use generate_video when the user asks you to create, produce, or make a video, clip, animation, or motion content from a text description. Provide a detailed prompt including subject, action, style, camera motion, and ambiance. Short cinematic prompts work best.
- Use animate_image when the user wants to bring a still image to life — the last generated image, an attached/pasted image, or a file on disk. Describe how the image should move or animate.
- Video generation takes 1–6 minutes depending on the provider and settings. Let the user know it may take a moment. Do not make multiple video requests in parallel.
- If a provider returns a validation error such as INVALID_ARGUMENT, do not retry the same request unchanged. Surface the provider error once, then adjust parameters or switch providers.
- Default settings: 8 seconds, 16:9 aspect ratio, 720p resolution. Only change these if the user explicitly requests different values.
- Google Veo supports 4, 6, or 8 second durations. 1080p and 4k require 8 seconds. Aspect ratios: 16:9 or 9:16. Generates audio natively.
- For Google Veo in this release, do not infer or force person-generation settings from the prompt. Let the provider defaults apply.
- xAI supports 1–15 second durations. Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. Resolutions: 480p or 720p.
- Generated videos are saved as MP4 files in the thread media folder and displayed inline in chat.
- Do NOT promise video editing, video extension, reference-image workflows, or fal-backed models — these are not available in this version.
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.
- 5d ago First seen · 37 lines · 14 tokens per session scan A f8ca7e0bd654
video_guide is a skill published in the GitHub repository siddsachar/row-bot (1,480 stars, last pushed 7d ago), licensed Apache-2.0. It adds 14 tokens to every session and 472 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ocr
Правила выбора между OCR (ocrimage) и Vision (describeimage) для обработки изображений. Триггер — пользователь загружает изображение с текстом или просит прочитать текст с фото.
ai-image-color-cycling
Generate an AI image, quantize it to a 256-color indexed palette, and produce BOTH a self-contained HTML artifact AND a perfect-loop animated GIF that bring the image to life via classic 1990s palette cycling — the trick where rotating palette entries makes water flow, fire flicker, and stars twinkle without ever…
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
image-to-cinematic-video
Turn a prompt or an existing image into a polished multi-scene cinematic short video using Seedance for clip generation, uguu.se for file hosting, and FFmpeg for last-frame extraction and crossfade stitching. Supports two modes — PARALLEL (multiple scenes from the same reference image, concurrent, 3 min total) and…
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.