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 commands/vallykrie/swarmgpt/codex-imagegengit clone --depth 1 https://github.com/Vallykrie/swarmGPTWrote 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/commands/vallykrie/swarmgpt/codex-imagegen)<a href="https://agentmods.dev/commands/vallykrie/swarmgpt/codex-imagegen"><img src="https://agentmods.dev/badge/commands/vallykrie/swarmgpt/codex-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 | $0.00029 | $0.00196 |
| Opus 5 | $0.00015 | $0.00098 |
| Sonnet 5 | $0.00006 | $0.00039 |
| Haiku 4.5 | $0.00003 | $0.00020 |
Grade A, and why
codex-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 4d 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.
What it actually says
Run the codex-imagegen skill (skills/codex-imagegen/SKILL.md in this
plugin — read it now and follow it exactly).
Arguments given: $ARGUMENTS
Treat the whole argument string as the image request. If it is empty, ask the user what image they want and where to save it, then proceed.
Follow the skill: build a detailed image prompt, pick an absolute output path
(ask only if no sensible default exists in the project), dispatch the codex
job with --sandbox workspace-write, verify by viewing the resulting file and
checking its real format, then deliver it. Multiple requested images are
dispatched in parallel, one codex job each, with distinct output paths.
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.
- 4d ago First seen · 19 lines · 29 tokens per session scan A 088b9e6de36e
codex-imagegen is a command published in the GitHub repository Vallykrie/swarmGPT (2 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 196 once invoked, about $0.0001 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 commands, from other repositories
audio
description: Synthesize, transcribe, or transform speech and audio with Modellix. argument-hint: [tts|stt|sts] [text or public audio URL] disable-model-invocation: true.
video
description: Generate a video with Modellix from a prompt, an image, or a source video. argument-hint: [prompt] [optional image or video URL] disable-model-invocation: true.
image
description: Generate an image with Modellix, or edit one when input images are given. argument-hint: [prompt] [optional image URL or path] disable-model-invocation: true.
generate-audio
Convert text to speech using 54+ AI voices in 8 languages.
generate-image
Generate images from text prompts using Flux Klein, Flux Schnell, or ZImageTurbo models.
transform-image
Transform images with style transfer and AI modifications.