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 skills add siddsachar/row-bot --skill designer_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/designer_guide)<a href="https://agentmods.dev/skills/siddsachar/row-bot/designer_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/designer_guide/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/siddsachar/row-bot/designer_guide"><img src="https://agentmods.dev/badge/skills/siddsachar/row-bot/designer_guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00016 | $0.04463 |
| Opus 5.5 | $0.00006 | $0.01785 |
| Sonnet 5.5 | $0.00003 | $0.00893 |
| Haiku 4.5 | $0.00002 | $0.00446 |
Grade A, and why
designer_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 1mo 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DESIGNER TOOL:
- You have designer tools that create/edit multi-page visual designs.
- Each project has a mode, a canvas aspect ratio, multi-page content, and an optional brand config.
- All designs are rendered as HTML/CSS in a sandboxed iframe preview.
Project modes (pick one — the mode dictates layout, canvas, and tool surface)
| mode | What it produces | page_kind | Default aspect | Canvas behaviour |
|---|---|---|---|---|
deck |
Slide deck (16:9 / 4:3 / 1:1 / 9:16) | slide | 16:9 (1920×1080) | Fixed body — width:Wpx; height:Hpx; overflow:hidden. Each page is a single slide. |
document |
A4 / Letter document pages | slide | A4 (794×1123) | Fixed page body — same fixed-frame rules as deck. |
landing |
Tall scrollable landing page | screen | landing (1440×3200 hint) | Tall scrollable. Use html,body{min-height:100vh;overflow-x:hidden} and a .page{max-width:1440px;margin:0 auto} wrapper. NEVER set body{overflow:hidden} or fixed pixel height. Use responsive units (vw, clamp(), %). |
app_mockup |
Phone or desktop UI prototype | screen | phone (390×844) | One device viewport per page/route. html,body{width:Wpx;height:Hpx;overflow:hidden}. In-content scrolling goes inside an inner .screen-body{overflow-y:auto}. |
storyboard |
Cinematic shot-by-shot board | shot | 16:9 (1920×1080) | Fixed-frame like deck. Each page = one shot with beat / caption / camera direction. |
The user picks mode in the New Design dialog. You can read it with designer_get_project and change it with designer_set_mode. Switching modes does NOT auto-resize the canvas — call designer_resize_project after designer_set_mode if you also want a different aspect.
Core page operations
designer_set_pages: Replace ALL pages. Use for new projects or full reworks. Input: list of{html, title, notes}.designer_update_page: Update a single page HTML. Input:index,html, optionaltitle.designer_add_page: Insert a new page. Useindex=-1to append.designer_delete_page: Remove a page by index. DESTRUCTIVE — requires user approval.designer_move_page: Reorder a page. Input:from_index,to_index.designer_get_project: Read project summary (mode, page titles, brand, dimensions). Call before any multi-page edit.designer_get_page_html: Read the full stored HTML for a single page. Call before full-page rewrites so you preserve existing assets and layout.designer_get_reference: Read a saved project reference by id or filename so you can reuse prior attachments without asking again.
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.
- 1mo ago First seen · 176 lines · 16 tokens per session scan A 3f920bf856ee
designer_guide is a skill published in the GitHub repository siddsachar/row-bot (1,632 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 4,463 once invoked, about $0.0001 per session on Opus 5.5. 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
dev2-design
Generate high-level design options for a feature. Presents 2-4 design alternatives with pros and cons. Sub-skill of the /dev workflow.
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.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".