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/improve-ui-ux)<a href="https://agentmods.dev/commands/oriolshhh/runware-image-mcp/improve-ui-ux"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/improve-ui-ux/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/improve-ui-ux"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/improve-ui-ux.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 | $0.00926 |
| Opus 5 | $0.00014 | $0.00463 |
| Sonnet 5 | $0.00005 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
improve-ui-ux 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 9d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/improve-ui-ux — Improve an existing interface
Purpose
Make a real existing route, flow, or component more usable, accessible,
responsive, coherent, and visually intentional without an uncontrolled redesign.
Use /spec-frontend instead when the user requests a major or drastic redesign
that should persist a detailed direction for approval before implementation.
Invocation
/improve-ui-ux <route/component> [goal or pain point]
Accepted input
A rendered route/component, user problem, screenshot/reference, usability issue, or request for a scoped visual and interaction polish pass.
This is the fast lane for reversible improvements. It is not the planning path for a new visual language, broad information-architecture change, or substantial existing-surface redesign.
Prerequisites
A runnable UI or reproducible component preview. If none exists, static review is allowed but the command cannot claim visual completion.
Procedure
- Reuse repository context and identify the exact user, task, target surface, desired degree of change, non-goals, preview command, and current design system.
- Use
browser-visual-validationto capture a comparable baseline at relevant viewports and states before editing. Record runtime, console, network, accessibility, overflow, and interaction failures. - Have
ux-reviewer,accessibility-reviewer,design-system-specialist, andfrontend-design-leadproduce one consolidated audit. Separate:- functional/usability/accessibility blockers;
- design-system inconsistencies;
- responsive/state gaps;
- visual hierarchy and craft improvements;
- subjective optional polish.
- Apply at most one enabled primary aesthetic pack (
frontend-design,taste-skill, orui-ux-pro-max). Applyemil-design-engineeringonly when interaction or motion is in scope. Do not load disabled packs as secret defaults. - Prioritize the smallest coherent improvement set by user impact, confidence, reversibility, and implementation cost. Preserve working brand and product behavior.
- Stop for approval if the set changes brand language, navigation/IA, shared design-system APIs, dependencies, or product behavior. Otherwise the command invocation authorizes the scoped reversible pass.
- Have
frontend-implementerapply the selected set using complete UI states, responsive behavior, accessible semantics/interactions, and focused tests. - Re-run the identical baseline scenarios. Have
visual-qa-testercompare before/after evidence and inspect console/network/runtime behavior. - Have
accessibility-reviewerindependently verify blockers; addmotion-design-reviewerwhen motion changed. Correct verified in-scope regressions. - Run applicable gates and report improved outcomes, evidence, files, tests, remaining polish, rejected suggestions, 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.
- 9d ago First seen · 90 lines · 27 tokens per session scan A 078aa8319550
improve-ui-ux 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 926 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
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
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.
revisar-ui
Auditoria visual retroativa de 6 pilares do código frontend implementado.
colorize
Introduce or rework color strategy.
extract
Pull repeated patterns into reusable components and design tokens.