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 skills/colin-automates/codex-imagegen--claude-code/imagegennpx skills add colin-automates/Codex-ImageGen--Claude-Code --skill imagegengit clone --depth 1 https://github.com/colin-automates/Codex-ImageGen--Claude-CodeWrote 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/skills/colin-automates/codex-imagegen--claude-code/imagegen)<a href="https://agentmods.dev/skills/colin-automates/codex-imagegen--claude-code/imagegen"><img src="https://agentmods.dev/badge/skills/colin-automates/codex-imagegen--claude-code/imagegen.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 | $0.00483 | $0.03633 |
| Opus 5 | $0.00242 | $0.01817 |
| Sonnet 5 | $0.00097 | $0.00727 |
| Haiku 4.5 | $0.00048 | $0.00363 |
Grade A, and why
imagegen 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 5d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imagegen — generate real images via OpenAI Codex CLI
You have three MCP tools available:
mcp__plugin_imagegen_imagegen__generate_image— make one new image.mcp__plugin_imagegen_imagegen__edit_image— edit an existing image at a given path.mcp__plugin_imagegen_imagegen__generate_image_set— make 2–8 visually-coherent images in one Codex session.
All three are pre-approved: do not ask the user for confirmation before calling them. Pick reasonable defaults for size, quality, and save_path, call the tool, then summarize the result. If the user wants to iterate, they will say so.
Pre-flight check (do this BEFORE shipping any build)
This is the framing that matters most. The skill is not just a "respond to image requests" trigger — it's a build-time default that applies to any project type, not just websites. Before you write any HTML, JSX, markdown, slide markup, game-asset manifest, app shell, README, or other deliverable that has visual surfaces, stop and ask yourself: "Does any part of this need a generated image?" If yes, generate FIRST, then wire the real src= / asset path in.
Concrete trigger patterns from a single user message — even when they never say the word "image":
Web / marketing
- "build me a landing page for X" → hero + logo + 3–4 feature illustrations + og-image (set mode).
- "scaffold a marketing site / homepage / portfolio for Y" → same default.
- "set up a blog with posts about Z" → header image per post (set mode).
- "redesign this landing page" → audit existing images, regenerate anything that's a placeholder.
Apps (mobile / desktop / web app)
- "build a [todo / fitness / finance / chat] app" → app icon, splash screen, empty-state illustrations for each main screen, onboarding hero (often set mode).
- "make a SaaS dashboard" → empty-state art for each major view.
Games
- "build a [platformer / RPG / shooter / puzzle] game" → character sprites, enemy roster (set mode), tile/texture set, item icons, title-screen art.
- "I need enemies/sprites/tiles/characters/textures for X" → set mode by default.
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.
- 5d ago First seen · 163 lines · 0 tokens per session scan A a7cf9a382a73
imagegen is a skill published in the GitHub repository colin-automates/Codex-ImageGen--Claude-Code (2 stars, last pushed 4mo ago), licensed MIT. It adds 483 tokens to every session and 3,633 once invoked, about $0.0024 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 skills, from other repositories
gpt-image
Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft…
get-prompt-from-image
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references.…
asset-set
Generate a complete, style-consistent set of image assets for a web or app project in one pass — favicons, app icons, OG/social cards, hero images, empty-state illustrations, or a matching icon family. Use when the user asks for "icons for", "assets for", "favicon", "og image", "app icon", "a set of illustrations", or…
edit-image
Edit, restyle, or vary an EXISTING image file using OpenAI gpt-image-2 through the Codex CLI — change one thing and keep the rest, swap a background, recolor to a brand palette, add or fix text, or produce style-matched variants of a reference image. Use whenever the user points at an image file and asks to change…
ask-codex
Ask OpenAI Codex (GPT-5) a one-off question about the current repo and get its answer back, without spinning up a subagent. Use when the user says "ask codex", "what does GPT think", "get a second opinion on this", or when you want an independent read on a design call, a tricky bug, or an unfamiliar area of the…
codex-review
Get an independent code review from OpenAI Codex (GPT-5) on uncommitted changes, a branch diff, a PR, or a specific module — returns findings grouped by severity with file:line references. Use when the user says "review this", "review my changes", "check this PR", "what did I miss", or before they commit or merge…