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 skills add AceDataCloud/OpenAIMCP --skill gpt-imagegit clone --depth 1 https://github.com/AceDataCloud/OpenAIMCPWrote 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/skills/acedatacloud/openaimcp/gpt-image)<a href="https://agentmods.dev/skills/acedatacloud/openaimcp/gpt-image"><img src="https://agentmods.dev/badge/skills/acedatacloud/openaimcp/gpt-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.
<a href="https://agentmods.dev/skills/acedatacloud/openaimcp/gpt-image"><img src="https://agentmods.dev/badge/skills/acedatacloud/openaimcp/gpt-image.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00053 | $0.00422 |
| Opus 5.5 | $0.00021 | $0.00169 |
| Sonnet 5.5 | $0.00011 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
gpt-image 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 today.
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
GPT Image by Ace Data Cloud
Use the MCP tools installed by this plugin. Match tools by their suffix because goose namespaces them with gpt-image-by-acedatacloud.
- Read
../../README.mdfor installation and credential setup. The service API key belongs inACEDATACLOUD_API_TOKENin the environment that starts goose; never ask the user to paste it into chat. - A free connection/reference check uses
gpt_image_list_models. Static reference success is not a paid generation or a billing result. - For an explicitly requested generation/edit, inspect the installed tool schema first. Use
gpt_image_generate,gpt_image_editas applicable. Do not invent model defaults or silently substitute another model/service. - Confirm current account access, balance and price; preserve any user spending cap. Do not generate merely to test installation or check progress.
- After one submission, retain the returned task ID. Use
gpt_image_get_taskto query that same ID, with the exact ID argument name from the schema. A pending result is not success; stop at terminal failure and preserve upstream meaning. Do not submit another generation to poll. - Report complete only with an explicit successful terminal status and returned media URLs. Never fabricate audio/image/video URLs or claim a unique billing record without checking the account's actual usage.
- When using GPT Image, choose a public
gpt-image-*model explicitly. This image plugin does not offer chat, embeddings, audio or Nano Banana as automatic fallbacks.
The installed server is the canonical published --profile gpt-image surface, including gpt_image_list_tasks for bounded history lookup. Model must be explicitly supplied for generate/edit; inspect its enum rather than inventing an alias.
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.
- today First seen · 20 lines · 53 tokens per session scan A d35cddf97af9
gpt-image is a skill published in the GitHub repository AceDataCloud/OpenAIMCP (1 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 422 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
anatomy
Explain an idea as an interactive isometric machine figure.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
grounded-citations
Ground answers and documents in cited, verifiable sources.
hermes-agent-skill-authoring
Author in-repo SKILL.md files: frontmatter and structure.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.