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 agentmods add rules/prenats/claude-imagine/image-generationgit clone --depth 1 https://github.com/prenats/claude-imagineWrote 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/prenats/claude-imagine/image-generation)<a href="https://agentmods.dev/rules/prenats/claude-imagine/image-generation"><img src="https://agentmods.dev/badge/rules/prenats/claude-imagine/image-generation.svg" alt="Measured on agentmods" 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 | $0.00382 | $0.00382 |
| Opus 5 | $0.00191 | $0.00191 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
image-generation 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 4d 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.
What it actually says
Image Generation (claude-imagine MCP)
When the user needs an image (hero, icon, product photo, avatar, banner, etc.):
- Engineer a prompt (150–250 words): scene, lighting, atmosphere, camera/lens, color grading, materials, style markers, quality anchors. Comma-separated phrases, not full sentences. No negative terms in the main prompt.
- Call the MCP tool
generate_imageon serverclaude-imaginewith the crafted prompt asdescription. - Pick the right type: ICON, THUMBNAIL, BACKGROUND, TEXTURE (fast); AVATAR, CONTENT, BANNER, PRODUCT (standard); LOGO, HERO, FEATURED (high).
- Save to a sensible
output_pathin the project (default:generated/<slug>.png).
Use list_capabilities to see configured models and image types.
Use check_server before batch generation.
Use batch_generate when multiple images are needed at once.
Never
- Placeholder services (picsum, placehold.it, via.placeholder, lorempixel)
- Empty
src=""on<img>tags - Skip prompt engineering and pass a one-line description to
generate_image
Inline generation while coding
When building HTML/UI and an <img> is needed, generate in context using the surrounding theme, palette, and copy — do not defer to stock placeholders.
Reference
| Tier | Types |
|---|---|
| Fast | ICON, THUMBNAIL, BACKGROUND, TEXTURE |
| Standard | AVATAR, CONTENT, BANNER, PRODUCT |
| High | LOGO, HERO, FEATURED |
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.
- 4d ago First seen · 36 lines · 382 tokens per session scan A dd5109ae9fcd
image-generation is a cursor rule published in the GitHub repository prenats/claude-imagine (1 stars, last pushed 2mo ago), licensed MIT. It adds 382 tokens to every session, about $0.0019 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 cursor rules, from other repositories
cursorrules
You have access to the local InvokeAI creative engine: image generation (txt2img / img2img / masked inpaint / 4x upscale), queue control, model management (HF/Civitai installs), gallery/board organization, and workflow library management.
prompt-to-asset
Asset generation — route, rewrite, generate, validate. Never send transparency requests to Imagen/Gemini.
cascade-img
Do not edit by hand — edit that block in AGENTS.md and regenerate. -->.
080-creative-phase-metrics
description: WHEN entering a creative phase ENSURE comprehensive exploration and validation globs: ["/.md", "/.mdc"] alwaysApply: true.
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.