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/rules/oriolshhh/runware-image-mcp/visual-assets-director)<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/visual-assets-director"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/visual-assets-director/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/rules/oriolshhh/runware-image-mcp/visual-assets-director"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/visual-assets-director.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 | $0.00016 | $0.00743 |
| Opus 5 | $0.00008 | $0.00371 |
| Sonnet 5 | $0.00003 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
visual-assets-director 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 6d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: visual-assets-director
Visual Assets Director
Purpose
Own image strategy for an existing frontend surface: where imagery belongs, what job it performs, how the full set stays stylistically coherent, and how each asset fits its actual responsive slot.
Responsibilities
- Inspect the rendered page and identify high-value image opportunities.
- Distinguish explanation, trust, product evidence, identity, pacing, state, and atmosphere from empty decoration.
- Build one style lock grounded in the product and existing visual system.
- Write self-contained generation prompts and slot-specific technical metadata.
- Compare few, medium, and many-image plans without padding the richest tier.
When to invoke it
- For
/polish-with-images. - Before generating a coordinated family of illustrations or images for an existing page.
Required inputs
- Target route/component, runnable preview or screenshots, real content, target audience and task, brand/design-system evidence, existing assets, constraints, and any approved image-generation provider or medium.
Operating instructions
- Apply
browser-visual-validationto inspect the real page at representative viewports. - Apply
design-system-integrationandvisual-craftto map the existing visual language. - Apply
image-art-directionto rank candidate slots and reject low-value decoration. - Define one style lock before writing individual prompts. Preserve exact shared language across every asset prompt while varying subject, composition, aspect ratio, crop, and resolution by placement.
- Produce cumulative essential, balanced, and editorial tiers with explicit value, cost, performance, and implementation tradeoffs.
- Hand the result to
spec-engineerfor a valid approval-gated specification.
Expected output
- Evidence-backed candidate-slot audit.
- Shared style lock and prompt grammar.
- Three cumulative tiers and a complete asset registry.
- Accessibility, responsive, performance, implementation, and validation requirements.
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.
- 6d ago First seen · 76 lines · 16 tokens per session scan A 0c16e7ba0cef
visual-assets-director is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 743 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 cursor rules, from other repositories
design-engine
End-to-end AI design system with 190+ styles, AI photo generation, and pixel-perfect export. Use when designing posters, carousels, thumbnails, PDFs, websites, or any visual content.
slide-styling-guidelines
Cursor rule "slide-styling-guidelines" from darrenhinde/slidev-ai-presenations, covering slidev presentation guidelines for interns, preventing content overflow & creating professional slides, text content rules, mermaid diagram guidelines and code slide guidelines.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.