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.
git 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/commands/oriolshhh/runware-image-mcp/frontend-design)<a href="https://agentmods.dev/commands/oriolshhh/runware-image-mcp/frontend-design"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/frontend-design/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/commands/oriolshhh/runware-image-mcp/frontend-design"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/frontend-design.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 | $0.00884 |
| Opus 5 | $0.00014 | $0.00442 |
| Sonnet 5 | $0.00005 | $0.00177 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
frontend-design 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/frontend-design — Design and build a frontend surface
Purpose
Create a production-quality page, screen, or component whose visual direction comes from the product brief and whose quality is proven in the rendered app.
Invocation
/frontend-design <surface and product goal>
Accepted input
A new frontend request, product goal, target users, route/component, references, brand constraints, or an approved spec. Real content is preferred.
Prerequisites
A frontend repository or approved location for a new frontend. A runnable preview is required before visual completion can be claimed.
Procedure
- Reuse fresh
.agent/context/, inspect the relevant frontend, and discover its install, preview, test, styling, design-system, and browser-validation setup. - Normalize the brief: target user, primary task, surface, content, constraints, success criteria, and desired degree of visual change. Ask one small grouped blocker batch only when repository evidence and safe defaults cannot answer it.
- Have
design-system-specialistmap existing tokens, primitives, components, themes, typography, icons, stories, and closest precedents. - Have
frontend-design-leadcreate one direction usingfrontend-design-direction. Use at most one enabled primary pack amongfrontend-design,taste-skill, andui-ux-pro-max; optionally layeremil-design-engineeringfor motion. Disabled packs are not silently applied. - Define complete states, responsive transitions, accessibility requirements, content/copy, motion intent, reused primitives, tests, and browser acceptance.
- Present a compact direction before code. Stop for explicit approval when the request materially changes brand language, navigation/information architecture, shared design-system APIs, dependencies, or product behavior. For a clear, scoped and reversible request, the invocation itself authorizes implementation.
- Have
frontend-implementerimplement the smallest coherent version. Preserve repository patterns and require approval before adding dependencies. - Have
visual-qa-testerrunbrowser-visual-validationat representative narrow, medium, and wide states, including relevant loading/error/empty/success, keyboard/focus, long content, theme, zoom, and reduced-motion paths. - Route independent review to
accessibility-reviewerand, only when motion changed,motion-design-reviewer. Correct verified in-scope blockers once. - Run configured gates and report the direction, files, states, viewports, browser evidence, tests, remaining risks, and untested coverage.
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 · 83 lines · 27 tokens per session scan A dcfe712cc325
frontend-design is a command published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 884 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 2026-08-31.
Other commands, from other repositories
seed-create-component
A command for creating a new SEED Design component, including its source specification, recipes, React implementation, documentation, examples, and optional headless layer.
sddesign
Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.
craft
One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
spec-screenshot
Analyze website screenshots and generate detailed implementation specs.