A command-line helper for generating images with OpenAI’s image-generation model through Codex login. It explains how to check the Codex CLI installation and authentication before generating an image.

Use it to create images from prompts, choose sizes or quality settings, and place the generated files in a project.

It lets a logged-in Codex user generate images without setting up a separate API key. It also identifies missing installation or login steps before use.

How byungjunjang/slide-master configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to byungjunjang/slide-master. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/byungjunjang/slide-master/main/.claude/skills/codex-image/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/byungjunjang/slide-master

Made for: Claude Code.

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/byungjunjang/slide-master/codex-image/github.svg)](https://agentmods.dev/skills/byungjunjang/slide-master/codex-image)

Your own site

<a href="https://agentmods.dev/skills/byungjunjang/slide-master/codex-image"><img src="https://agentmods.dev/badge/skills/byungjunjang/slide-master/codex-image/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/byungjunjang/slide-master/codex-image"><img src="https://agentmods.dev/badge/skills/byungjunjang/slide-master/codex-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,808 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Excessive Agency · line 116
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
high Agent Snooping · line 178
Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
medium Rogue Agent · line 111
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

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	$0.00091	$0.02808
Opus 5.5	$0.00036	$0.01123
Sonnet 5.5	$0.00018	$0.00562
Haiku 4.5	$0.00009	$0.00281

Measured 1mo ago against content hash 941b658140ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Model requires a newer Codex | The model in `~/.codex/config.toml` is newer than the installed CLI. Suggest `npm install -g @openai/codex@latest`, or pass `-m <model>` for this run. Do not edit the user's config. |

.claude/skills/codex-image/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

codex-image — AI Image Generation via Codex OAuth

Generate images with OpenAI's gpt-image-2 model through Codex CLI. No API key is needed: Codex OAuth (ChatGPT login) handles authentication.

User-facing messages below are bilingual (EN / KO). Print the one that matches the user's chat language.

How it works

User prompt → Claude Code (/codex-image)
  → codex exec (OAuth token auto-managed)
    → built-in image_gen tool (gpt-image-2)
      → ~/.codex/generated_images/<session>/
        → copy to <out dir>/<filename>.png

OAuth tokens cannot call the OpenAI REST API directly (it returns 401), so generation goes through codex exec, which handles auth internally.

Step 1 — Verify Codex CLI & Auth

which codex 2>/dev/null && codex --version 2>/dev/null || echo "NOT_FOUND"

If NOT_FOUND, stop:

"Codex CLI not installed. Run npm install -g @openai/codex then codex login." "Codex CLI 없음. npm install -g @openai/codex 후 codex login 실행해."

codex login status 2>&1

If not "Logged in", stop:

"Codex login required. Run codex login in terminal. OAuth login enables image generation without API key." "Codex 로그인 필요. 터미널에서 codex login 실행. OAuth 로그인하면 API 키 없이 이미지 생성 가능."

Step 2 — Parse Arguments

Extract from $ARGUMENTS:

Flag	Values	Default	Description
`--size`	`1024x1024`, `1024x1536`, `1536x1024`, `auto`	`1024x1024`	Image dimensions
`--quality`	`low`, `medium`, `high`, `auto`	`auto`	Generation quality
`--out`	directory path (inside the project root)	project root	Save location
`--filename`	name without extension	`codex-image-<timestamp>`	Output filename stem
`-n`	1–10	`1`	Number of images
`--ref`	image file path, repeatable	none	Reference image attached to Codex (Step 4)

Remaining text → image prompt.

If the prompt is empty, ask via AskUserQuestion:

"What image should I generate? Enter a prompt." "어떤 이미지를 생성할까? 프롬프트를 입력해줘."

Read the full file on GitHub · 203 lines

Files

What ships with it

2 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.

1mo ago Changed · +17 lines 941b658140ec
2mo ago First seen · 186 lines · 91 tokens per session scan B 08e48085caeb

Subscribe to this mod's changes

codex-image is a skill published in the GitHub repository byungjunjang/slide-master (304 stars, last pushed 11d ago), licensed MIT. It adds 91 tokens to every session and 2,808 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media

codex-image next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-imagebyungjunjang/slide-master	Skill	304	11d ago	MIT	B	91	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

slide-master: Skill for Claude Code