imagine

imagine is a skill for Claude Code from marsmike/feinschmiede. It costs 26 tokens per session (405 once invoked), scanned A, original, MIT.

An image-generation command that creates illustrations, photos, or graphics from written prompts using Replicate or Gemini.

In plain words
What is it for?
Use it to make images for websites, presentations, mockups, social posts, or other project assets, with a chosen provider, model, aspect ratio, and output file.
Why use it?
It removes the need to create every visual by hand or switch between separate image-generation services. It also reports a clear error without making a paid request when no provider key is set.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the feinbild plugin — 3 skills, 3 commands shipped together

Good fit Use it to make images for websites, presentations, mockups, social posts, or other project assets, with a chosen provider, model, aspect ratio, and output file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marsmike/feinschmiede/imagine
Install

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.

Any agent
npx skills add marsmike/feinschmiede --skill imagine
Clone the repo
git clone --depth 1 https://github.com/marsmike/feinschmiede

Made for: Claude Code.

Or install feinbild, the plugin that ships this one along with the rest of its 3 skills, 3 commands.

Wrote 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.

agentmods badge for imagine

README.md
[![agentmods](https://agentmods.dev/badge/skills/marsmike/feinschmiede/imagine/github.svg)](https://agentmods.dev/skills/marsmike/feinschmiede/imagine)
Your own site
<a href="https://agentmods.dev/skills/marsmike/feinschmiede/imagine"><img src="https://agentmods.dev/badge/skills/marsmike/feinschmiede/imagine/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.

agentmods 80×15 button for imagine

Your own site · 80×15
<a href="https://agentmods.dev/skills/marsmike/feinschmiede/imagine"><img src="https://agentmods.dev/badge/skills/marsmike/feinschmiede/imagine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 405 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00405
Opus 5 $0.00013 $0.00202
Sonnet 5 $0.00005 $0.00081
Haiku 4.5 $0.00003 $0.00040

Measured 9d ago against content hash 9ac198fffc15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

imagine 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.

feinbild/skills/imagine/SKILL.md · 46 lines

What it actually says

feinbild — AI image generation

Quick Start

/imagine retro synthwave city skyline

See references/providers.md for examples.

feinbild is a command on your PATH. Requires a provider key in ~/.env (REPLICATE_API_KEY or GEMINI_API_KEY).

feinbild imagine --prompt "a calm mountain lake at dawn" --out lake.webp

Options: --provider (replicate/gemini), --model, --aspect-ratio (1:1 default, 16:9, 9:16, 4:3, 3:2, …), --out. Without a key the command prints a clean error and makes no paid call.

Providers

  • Replicate (default) — Flux models, fast, best text rendering for memes.
  • Gemini — free tier (500/day), great general quality.

Full model list, selection guide, and examples: references/providers.md.

Brand Design Systems

For images in the visual style of specific companies (Apple, Linear, Stripe, Vercel, etc.), fetch the brand's DESIGN.md from awesome-design-md — 76+ design systems as plain markdown.

URL: https://raw.githubusercontent.com/VoltAgent/awesome-design-md/main/designs/<brand>/DESIGN.md

Extract the brand's color palette, typography style, and visual language, then weave them into the --prompt (e.g., "clean Apple-style design with SF Pro typography, white background, subtle shadows, #007AFF accent blue").

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 9d ago First seen · 46 lines · 26 tokens per session scan A 9ac198fffc15

Subscribe to this mod's changes

imagine is a skill published in the GitHub repository marsmike/feinschmiede (3 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 405 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.

Related

Other skills, from other repositories

creo-image-prompt

Generate optimized image prompts for AI image generation models including DALL-E 3, Midjourney, Stable Diffusion XL, Flux, and others. Creates contextually appropriate, visually compelling prompts based on page content and brand style. Trigger keywords: image prompt, AI image, hero image, marketing image, generate…

oyusypenko/creo · 73 tokens

creo-image-generation

Generate marketing images using DALL-E 3 or ComfyUI (Stable Diffusion XL). Batch generation, optimization, cost estimation. Requires image-generation extension. Triggers on: /creo image-generation, generate images, DALL-E, ComfyUI.

oyusypenko/creo · 58 tokens

video-edit

AI-powered video editing toolkit. Trim, concat, overlay text/images, mix audio, generate voiceover, add transitions, and export with social media presets. Uses Gemini for intelligent edit suggestions. Use when: creating videos, editing clips, adding overlays, mixing audio, generating voiceovers, exporting for social…

floomhq/moto · 117 tokens

yc-video

Plan, audit, and score startup launch videos using YC-grade production standards. Use when: creating product launch teasers, scoring video quality for social distribution, planning narrative structure for LinkedIn/X autoplay, reviewing cold-audience effectiveness. Triggers: "launch video", "yc video", "score the…

floomhq/moto · 88 tokens

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work.

floomhq/moto · 58 tokens

slide-design

Visual design system for creating high-quality presentation slides (HTML, PPTX, or PDF). Use when designing pitch deck slides, presentation visuals, or any slide-based content. Covers layout composition, typography, color, data visualization, and visual hierarchy for 1920x1080 slide formats. Focuses on making slides…

floomhq/moto · 75 tokens