ai-image-creator

ai-image-creator is a skill for Claude Code, Codex from centminmod/my-claude-code-setup. It costs 136 tokens per session (7,379 once invoked), scanned A, original, MIT.

A tool for generating and editing PNG images with several AI image models, and for turning videos into written descriptions.

In plain words
What is it for?
Use it to create images, modify images from references, analyze existing images, or analyze videos for descriptions, captions, speaker information, locations, and counted events.
Why use it?
It gives image and video tasks a single command-line interface with selectable model providers.

Skill for Claude CodeCodex

About the project

my-claude-code-setup is a starter configuration and memory-bank template for Claude Code, providing project guidance and reusable setup for Claude Code sessions. Developers use it to organize Claude Code behavior, memory, commands, skills, subagents, hooks, and settings. The catalogue entries are components of this Claude Code workflow.

centminmod/my-claude-code-setup · 2,620 stars · on GitHub · threads.com

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.

agentmods
npx agentmods add skills/centminmod/my-claude-code-setup/ai-image-creator
Any agent
npx skills add centminmod/my-claude-code-setup --skill ai-image-creator
Clone the repo
git clone --depth 1 https://github.com/centminmod/my-claude-code-setup

Made for: Claude Code, Codex.

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 ai-image-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/centminmod/my-claude-code-setup/ai-image-creator.svg)](https://agentmods.dev/skills/centminmod/my-claude-code-setup/ai-image-creator)
Your own site
<a href="https://agentmods.dev/skills/centminmod/my-claude-code-setup/ai-image-creator"><img src="https://agentmods.dev/badge/skills/centminmod/my-claude-code-setup/ai-image-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,379 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00136 $0.07379
Opus 5 $0.00068 $0.03689
Sonnet 5 $0.00027 $0.01476
Haiku 4.5 $0.00014 $0.00738

Measured 6d ago against content hash 12d0696dc5df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ai-image-creator scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/composite-banners.py, scripts/generate-image.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

For full API formats, response schemas, BYOK configuration, and curl examples:
.claude/skills/ai-image-creator/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Image Creator

Generate PNG images via multiple AI models, routed through Cloudflare AI Gateway BYOK or directly via OpenRouter/Google AI Studio.

Model Selection

When the user mentions a model keyword in their image request, use the corresponding --model flag:

Keyword Model Use When User Says
gemini Google Gemini 3.1 Flash (default) "gemini", "generate an image" (no model specified)
geminipro Google Gemini 3 Pro "geminipro", "gemini pro", "use gemini pro"
riverflow Sourceful Riverflow v2 Pro "riverflow", "use riverflow"
flux2 FLUX.2 Max "flux2", "flux", "use flux"
seedream ByteDance SeedDream 4.5 "seedream", "use seedream"
gpt5 OpenAI GPT-5 Image "gpt5", "gpt5 image", "use gpt5"
gpt5.4 OpenAI GPT-5.4 Image 2 "gpt5.4", "gpt-5.4 image", "use gpt5.4"

Instructions

Routing check: If the user asks to describe, analyze, or explain an existing image (not generate a new one), skip directly to the Image Analysis (--analyze) section below. No prompt enhancement or output path needed.

Video routing: If the user asks to describe, analyze, or explain a video (or wants a text description of a clip to seed/extend a video prompt), skip directly to the Video Analysis (--analyze-video) section below.

Step 1: Write Prompt

For long or complex prompts (recommended), write to ${CLAUDE_SKILL_DIR}/tmp/prompt.txt using the Write tool:

Write prompt text to ${CLAUDE_SKILL_DIR}/tmp/prompt.txt

For short prompts (under 200 chars, no special characters), pass inline via --prompt.

Read the full file on GitHub · 478 lines

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. 6d ago First seen · 478 lines · 136 tokens per session scan A 12d0696dc5df

Subscribe to this mod's changes

ai-image-creator is a skill published in the GitHub repository centminmod/my-claude-code-setup (2,620 stars, last pushed 3d ago), licensed MIT. It adds 136 tokens to every session and 7,379 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

memory-bank

Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…

josiahcrackle9631/memory-bank · 199 tokens

chatkit-integration

Foundation skill for integrating OpenAI ChatKit framework with custom backends. This skill should be used for initial ChatKit setup including server implementation, React component integration, authentication, context injection, and database persistence. For streaming UI patterns use chatkit-streaming. For interactive…

mjunaidca/mjs-agent-skills · 66 tokens

chatkit-actions

Implements interactive widget actions and bidirectional communication patterns for ChatKit. This skill should be used when building AI-driven interactive UIs with buttons, forms, entity tagging (@mentions), composer tools, and server-handled widget actions. Covers the full widget lifecycle from creation to replacement.

mjunaidca/mjs-agent-skills · 60 tokens

shadcn-ui

Build beautiful, accessible UIs with shadcn/ui components. Use this skill when creating forms, dialogs, tables, sidebars, or any UI components in Next.js. Covers installation, component patterns, react-hook-form integration with Zod validation, and dark mode setup.

mjunaidca/mjs-agent-skills · 60 tokens

sqlmodel-database

Design and implement database schemas using SQLModel with sync and async patterns. Use this skill when creating database models, setting up Neon PostgreSQL connections, defining relationships (one-to-many, many-to-many), implementing FastAPI dependency injection, or migrating schemas. Covers both sync Session and…

mjunaidca/mjs-agent-skills · 65 tokens

multi-agent-patterns

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

mjunaidca/mjs-agent-skills · 38 tokens