A skill for generating or editing images through OpenAI’s Codex image service, using text prompts or reference images.

It helps turn descriptions into image files and modify existing images, with options for choosing an output path, model, and effort level.

It provides a defined way to create images without manually handling the service’s login token and image-generation requests.

codex-image — Skill for Claude Code and Codex by OpenMinis: A skill for generating or editing images through OpenAI’s…

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/openminis/minisskills/codex-image

Any agent

npx skills add OpenMinis/MinisSkills --skill codex-image

Clone the repo

git clone --depth 1 https://github.com/OpenMinis/MinisSkills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/openminis/minisskills/codex-image.svg)](https://agentmods.dev/skills/openminis/minisskills/codex-image)

Your own site

<a href="https://agentmods.dev/skills/openminis/minisskills/codex-image"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/codex-image.svg" alt="Measured on agentmods" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5	$0.00089	$0.01086
Opus 5	$0.00044	$0.00543
Sonnet 5	$0.00018	$0.00217
Haiku 4.5	$0.00009	$0.00109

Measured 5d ago against content hash 2ffe4029bb45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-image scanned grade B 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/codex_image_edit.py, scripts/codex_image.py, scripts/get_auth.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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- On success → saves token to `~/.chatgpt_auth.json` (chmod 600, token + timestamp only)

codex-image/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Image Generation

Generate images via chatgpt.com/backend-api/codex/responses using the image_generation tool (gpt-image-2).

Requirements

A ChatGPT account (token is fetched automatically via browser session)
No manual token setup needed — the skill handles auth automatically

Auth Token Resolution (in order)

--token argument (CLI only)
CODEX_IMAGE_TOKEN environment variable
--token-file argument (CLI only)
~/.chatgpt_auth.json cache (valid for 8 hours)
Auto login flow — fetches from https://chatgpt.com/api/auth/session via minis-browser-use:
- If already logged in → token extracted and saved to cache immediately
- If not logged in → opens chatgpt.com/auth/login in the browser, then polls every 10s in a new tab for up to 5 minutes
- On success → saves token to ~/.chatgpt_auth.json (chmod 600, token + timestamp only)
- Token is never printed to stdout or logs — it stays in the cache file only

Usage

Text-to-image

python3 scripts/codex_image.py "a cute rabbit on a light background" \
  --output rabbit.png \
  --model gpt-5.4 \
  --effort low

Image-to-image / reference image

python3 scripts/codex_image_edit.py "turn this person into a cinematic iOS AI assistant portrait" \
  --image reference.jpg \
  --output portrait.png \
  --model gpt-5.4 \
  --effort low

codex_image_edit.py encodes the local reference image as a base64 data URL and sends it as multimodal input (input_text + input_image) to the same Codex responses endpoint, then asks the image_generation tool to create a new image from the reference.

Parameters

Parameter	Default	Description
`prompt`	(required)	Image description or edit instruction
`--image`	(edit only, required)	Local reference image path for image-to-image generation
`--output`	`codex_image.png` / `codex_image_edit.png`	Output file path
`--model`	`gpt-5.4`	Codex model
`--effort`	`low`	Reasoning effort: low/medium/high
`--token`	-	Access token directly (skips auto auth; text-to-image script only)
`--token-file`	-	File containing token (skips auto auth; text-to-image script only)

Read the full file on GitHub · 93 lines

Files

What ships with it

3 files 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.

5d ago First seen · 93 lines · 89 tokens per session scan B 2ffe4029bb45

Subscribe to this mod's changes

codex-image is a skill published in the GitHub repository OpenMinis/MinisSkills (396 stars, last pushed 16d ago), licensed MIT. It adds 89 tokens to every session and 1,086 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

codex-image