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 Oriolshhh/runware-image-mcp --skill visual-craftgit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/visual-craft)<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/visual-craft"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/visual-craft/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/oriolshhh/runware-image-mcp/visual-craft"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/visual-craft.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 | $0.00027 | $0.00885 |
| Opus 5 | $0.00014 | $0.00443 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
visual-craft 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 8d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Craft
Purpose
Turn an existing interface into a coherent, product-specific visual system without replacing its brand, design system, or usability with fashionable defaults.
This is a concise HarnessKit adaptation informed by the MIT-licensed
frontend-ui-engineering skill from addyosmani/agent-skills and baseline-ui
from ibelick/ui-skills. Exact provenance is recorded in
references/frontend/sources.md.
When to use it
- When a rendered page or flow needs a material visual redesign.
- When hierarchy, density, typography, color, spacing, or component treatment feels generic, inconsistent, or recognizably AI-generated.
Instructions
- Inspect the real rendered surface, nearby product screens, brand assets, design tokens, components, content, and supported themes. Record what must remain recognizable and what demonstrably fails.
- State one visual thesis tied to the product, audience, content, and primary task. Reject any direction that could be transplanted unchanged into an unrelated SaaS product.
- Define composition and hierarchy before decoration: reading order, primary action, information density, grouping, alignment, and deliberate asymmetry or emphasis where it serves the task.
- Define restrained typography roles with actual families or existing tokens, sizes, weights, line heights, measure, numeric treatment, and responsive behavior. Test real long and short content.
- Define semantic color roles for surfaces, text, borders, actions, feedback, selection, and focus. Preserve contrast and non-color cues. Do not default to purple-blue gradients, glass, glow, or a new palette without product evidence.
- Use the repository spacing scale. Specify page rhythm, component density, alignment anchors, section transitions, and intentional exceptions. Reject mechanically equal gaps, giant empty bands, and arbitrary one-off values.
- Make radius, border, elevation, iconography, imagery, and data visualization form one system. Avoid rounded-container soup, repetitive equal-card grids, random blobs, emoji-as-product-icons, and decorative charts without meaning.
- Specify every control's visible hover, active, focus, disabled, pending,
success, and error treatment when applicable. Coordinate behavior and motion
with
ui-state-design,accessible-ui-engineering, andmotion-design. - Use real content and honest data. Do not invent testimonials, metrics, product claims, or filler decoration to make the composition look complete.
- Compare baseline and proposed/final rendered evidence. Prefer fewer, stronger decisions over adding visual effects until the page feels different.
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.
- 8d ago First seen · 74 lines · 27 tokens per session scan A 623adbeaf349
visual-craft is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 885 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.