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 frontend-guidelinesgit 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/frontend-guidelines)<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/frontend-guidelines"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/frontend-guidelines/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/frontend-guidelines"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/frontend-guidelines.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 | $0.00022 | $0.00779 |
| Opus 5 | $0.00011 | $0.00390 |
| Sonnet 5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
frontend-guidelines 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Guidelines
Purpose
Keep frontend implementation usable, accessible, maintainable, and coherent with the product's design system instead of accumulating fragile component spaghetti.
When to use it
- Implementing or reviewing rendered UI, routes, components, client state, forms, navigation, design-system usage, or visual behavior.
- Changing loading, empty, error, success, permission, or offline states.
- Adding responsive behavior, animation, browser interactions, or accessibility behavior.
- Improving an existing interface through
/frontend-design,/improve-ui-ux,/ui-review, or frontend tasks inside/implement.
Instructions
- Reuse existing design tokens, primitives, layout patterns, and component conventions before creating new styles or components.
- Separate responsibilities: data loading, state transitions, presentation, form validation, and side effects should not collapse into one tangled component when they change for different reasons.
- Model the full state matrix: loading, empty, success, error, validation, permission, disabled, optimistic/pending, and long-content states.
- Build semantic, keyboard-operable UI first. Controls need names, roles, focus order, visible focus, labels, error association, and recoverability.
- Make layout content-driven and responsive. Verify mobile, tablet/desktop, zoom/reflow, long text, missing media, and narrow containers.
- Keep client state minimal and colocated. Lift state only when multiple owners truly need it; avoid duplicating server/cache state in local component state.
- Preserve performance basics: avoid unnecessary rerenders, unbounded effects, layout thrash, oversized bundles, and client-only work that could stay server side in the repository's framework.
- Use motion only when it communicates state or improves comprehension. Respect reduced motion and avoid blocking interaction.
- Validate in a real browser for user-facing changes. Check relevant viewports, states, keyboard paths, console errors, network failures, and screenshots when visual quality matters.
- Add tests where stable: component/interaction tests for behavior, integration tests for flows, and visual/browser evidence for presentation-sensitive work.
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 · 77 lines · 22 tokens per session scan A cc5507aa450c
frontend-guidelines is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 779 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
image-compare
Compare two image files on disk and report what changed, region by region. Trigger on "what changed between these two images", "diff these PNGs", "did this render drift", "compare screenshots/exports/renders".
Cypress v14 Component Testing
Component testing patterns with Cypress v14 including React, Vue, and Angular component mounting, custom mount commands, interaction testing, visual snapshots, and integration with Vite and Webpack bundlers.
visual-qa-testing
Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
review-screenshot
A standard workflow for taking screenshots to check a user interface, using a dedicated review process for different verification modes.
visual-regression-lab
Compare captures; stitch lazy/animated pages.