Menu

Individual skill

codex-image-plugin

Generate or edit raster images through an OpenAI-compatible image API. Use when the user provides an image API URL and key, asks to use a configured image model, lists available image models, or requests new images, reference-image edits, compositing, masks, cleanup, mockups, or illustrations.

plugins/zlsbksdxl/codex-image-plugin/skills/codex-image-plugin/SKILL.md

Read pinned source

Source commit d780783eba4ecc7c8b9429f95c9362df95f07c61

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,537
Repository last updated
Nov 7, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Codex Image Plugin

Use `scripts/image.py` as the API wrapper. It accepts an explicit endpoint URL, API key, and model, or reads them from `OPENAI_BASE_URL`/`OPENAI_API_KEY`/`IMAGE_MODEL` and the active Codex provider in `~/.codex/config.toml` (`base_url`, `OPENAI_API_KEY`, `image_model`). The selected `--model` is passed through unchanged, so the endpoint can expose any compatible image model. Do not print, persist, or reuse a Codex session bearer token as an image API key.

## Workflow

1. Decide whether the request is `models`, `generate`, or `edit`.
2. If the user supplied a URL and key, pass them with `--base-url` and `--api-key` or use environment variables. Prefer environment variables when the key should not appear in shell history.
3. Use `models` to inspect the endpoint before choosing a model.
4. For edits, obtain the actual input files first. Keep source images unchanged and write new results by default.
5. Save user-facing results under `outputs/` unless the user requests another path, then inspect the result and report exact paths.

## List available models