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.
/plugin marketplace add Wangnov/gpt-image-2-skillnpx agentmods add plugins/wangnov/gpt-image-2-skill/gpt-image-2-skillgit clone --depth 1 https://github.com/Wangnov/gpt-image-2-skillWrote 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/plugins/wangnov/gpt-image-2-skill/gpt-image-2-skill)<a href="https://agentmods.dev/plugins/wangnov/gpt-image-2-skill/gpt-image-2-skill"><img src="https://agentmods.dev/badge/plugins/wangnov/gpt-image-2-skill/gpt-image-2-skill.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
gpt-image-2-skill 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 6d 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
{
"name": "gpt-image-2-skill",
"version": "0.7.3",
"description": "GPT Image 2 CLI as a Claude Code skill: OpenAI gpt-image-2 + Codex image_generation under one command surface, with masks, transparent backgrounds, custom sizes up to 4K, and structured JSON / JSONL progress output.",
"author": {
"name": "wangnov",
"url": "https://github.com/Wangnov"
},
"homepage": "https://github.com/Wangnov/gpt-image-2-skill",
"repository": "https://github.com/Wangnov/gpt-image-2-skill",
"license": "MIT",
"keywords": [
"image-generation",
"openai",
"codex",
"gpt-image-2",
"skill"
],
"skills": [
"./skills/gpt-image-2-skill"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 191 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 6d ago First seen · 23 lines scan A 3aa2ac20e8c1
gpt-image-2-skill is a plugin published in the GitHub repository Wangnov/gpt-image-2-skill (134 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
gpt-image
OpenAI GPT Image 2 prompt gallery, image prompt library, agentic skill + CLI. Gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for skill-capable agent runtimes.
pake
Package any website or local web build into a lightweight desktop app with Pake CLI.
ai-business-skills
144 bilingual marketing skills (75 VN + 69 Global) for AI agents — strategy, content, performance, design production, leader ops, personal brand, and an AI Marketing OS. Vietnam 2025-2026 benchmarks plus US/EU/SEA/LATAM.
hinge-profile-optimizer
Research-backed Hinge profile audits, photo strategy, prompt writing, settings review, and implementation support.
shots
Ship store-ready App Store screenshots in minutes from your coding agent. Shots researches competing listings, then generates, revises, and translates screenshots and icons from your real app context.
swarmgpt
Make Codex your default writer and image generator: your agent plans and reviews while parallel codex exec (GPT-5.6) sessions do the writing, plus a codex-imagegen skill that generates real images through Codex's built-in imagegen tool.