What is openai-image-generator?

An image-generation workflow that creates the article images defined in an image prompt file and saves them in a format the WordPress publisher can use.

It generates cover and section images for articles according to their assigned image slots and configured image count.

It removes the need to generate each planned article image manually and can use a configured provider fallback when generation fails.

openai-image-generator — Skill for Claude Code by XuanRanL

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 XuanRanL/loamwright-SEO-Skill --skill openai-image-generator

Clone the repo

git clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-Skill

Made for: Claude Code.

Or install xuanran-seo-blog-writer, the plugin that ships this one along with the rest of its 68 skills, 34 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/openai-image-generator/github.svg)](https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/openai-image-generator)

Your own site

<a href="https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/openai-image-generator"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/openai-image-generator/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/openai-image-generator"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/openai-image-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,749 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.01749
Opus 5	$0.00046	$0.00874
Sonnet 5	$0.00018	$0.00350
Haiku 4.5	$0.00009	$0.00175

Measured 7d ago against content hash 9616c98aad6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

openai-image-generator 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 7d 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.

subskills/image/openai-image-generator/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenAI Image Generator

Generates every image slot in image-prompts.json (the count comes from brief.image_count via scripts/_core/image_policy.py — default 6, max 8) using the canonical openai_image_pipeline.py script. This skill consolidates what used to be Stage 27c (submit) + Stage 27d (poll) into a single call.

The pipeline routes to the configured PROVIDER CHAIN (scripts/_core/image_provider.py): since 2026-06-17 the primary is vertex-gemini — Google Vertex AI express mode serving Gemini 3 Pro Image (Nano Banana Pro) at true 4K (~16MP, downscaled to the requested pixel size), ~10x cheaper than OpenAI with better text rendering. The fallback is official OpenAI (gpt-image-2, honest 4K, ~$1.67/img). Every newapi gpt-image-2 relay (chatgpt-code / openclawroot / llmtoken / yunxiangpnv) was DISABLED on 2026-06-17 after all were found to silently degrade 4K to ~1.5MP (shared "GPT-Image-2-4k distributor" upstream). Mode is FORCED realtime (config.yaml :: image.default_mode: realtime; neither Vertex nor relays support the OpenAI Batch API). Each slot tries the primary, then auto-falls-back to official OpenAI on failure. Writes wp_publisher-compatible images.json.

The vertex-gemini provider is NOT OpenAI-compatible — it uses Vertex express generateContent + generationConfig.imageConfig (aspectRatio + imageSize="4K") with an AQ.-prefix API key via the x-goog-api-key header, handled by a dedicated branch (openai_image_pipeline._generate_vertex_gemini). Set up via config.yaml :: image.providers with protocol: vertex_gemini. See memory [[reference-vertex-gemini-4k-image-recipe]].

Why realtime + provider chain (vs the old batch-first pattern)

The old submit → awaiting-images → scheduled poller (batch-first) flow had failure modes:

Operator polled once at +5 min, saw validating, abandoned.
Batch API genuinely failed (HTTP 400 / expired) but the poller had no fallback.
--mode auto against a relay-primary setup is the worst case: it tries official batch FIRST (bypassing the relay), waits ~25 min, then falls back to realtime.

Read the full file on GitHub · 126 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.

7d ago First seen · 126 lines · 0 tokens per session scan A 9616c98aad6c

Subscribe to this mod's changes

openai-image-generator is a skill published in the GitHub repository XuanRanL/loamwright-SEO-Skill (49 stars, last pushed 24d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,749 once invoked, about $0.0005 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.

Claude Code Creative and media ai-search blog-automation chatgpt claude-plugin content-marketing

c2pa-metadata

Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…

indranilbanerjee/digital-marketing-pro · 183 tokens

ad-creative

Generate 3-5 ad copy variations per platform — headlines, descriptions, and CTAs formatted to Google, Meta, LinkedIn, TikTok, X, and Pinterest specs — each scored 1-10 with policy-compliance flags, A/B testing groupings, and a message-match check against the landing page. Triggers on…

indranilbanerjee/digital-marketing-pro · 162 tokens

citedy-content-writer

From topic to published blog post in one conversation — generate SEO- and GEO-optimized articles with AI illustrations and voice-over in 55 languages, create social media adaptations for 9 platforms, set up automated content sessions, and manage product knowledge base. End-to-end blog autopilot. Powered by Citedy.

citedy/adclaw · 70 tokens

openai-image-generator