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 gpt-img-2/image3-prompt-mcp --skill gpt-image-2-prompt-architectgit clone --depth 1 https://github.com/gpt-img-2/image3-prompt-mcpWrote 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/gpt-img-2/image3-prompt-mcp/gpt-image-2-prompt-architect)<a href="https://agentmods.dev/skills/gpt-img-2/image3-prompt-mcp/gpt-image-2-prompt-architect"><img src="https://agentmods.dev/badge/skills/gpt-img-2/image3-prompt-mcp/gpt-image-2-prompt-architect/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/gpt-img-2/image3-prompt-mcp/gpt-image-2-prompt-architect"><img src="https://agentmods.dev/badge/skills/gpt-img-2/image3-prompt-mcp/gpt-image-2-prompt-architect.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 | $0.00084 | $0.01623 |
| Opus 5 | $0.00042 | $0.00812 |
| Sonnet 5 | $0.00017 | $0.00325 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
gpt-image-2-prompt-architect 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT Image 2 Prompt Architect
This skill turns loose creative ideas into cleaner GPT Image 2 prompt packs with stronger subject control, composition, text rendering, reference-image handling, and revision loops.
Canonical links
- Docs: https://image3.org/docs/gpt-image-2-prompt-architect
- Demo: https://image3.org/models/gpt-image-2
- Create: https://image3.org/ai-image
- Prompt gallery: https://image3.org/prompts/gpt-image-2
- Raw SKILL.md: https://image3.org/skills/gpt-image-2-prompt-architect/SKILL.md
- Prompt guide: https://image3.org/blog/gpt-image-2-prompt-guide
- Product photo prompts: https://image3.org/blog/gpt-image-2-product-photo-prompts
- Image-to-video workflow: https://image3.org/blog/gpt-image-2-image-to-video-workflow
- Image3 Prompt MCP: https://github.com/gpt-img-2/image3-prompt-mcp
- OpenClaw listing: https://clawhub.ai/gpt-img-2/skills/gpt-image-2-prompt-architect
Provenance and safety
- Maintained around the public Image3 prompt workflow, prompt gallery, and documentation on
image3.org. - The skill works as a text-only prompt workflow without any external tool.
- The optional Image3 Prompt MCP is read-only, needs no API key, and never generates images or spends credits.
- Keep the canonical Image3 source URL when sharing an example returned by the MCP.
When to use
- The user has a rough AI image idea and wants a stronger GPT Image 2 prompt
- The user wants product photos, ecommerce listing images, lifestyle ads, packaging mockups, or detail shots
- The user needs UI mockups, posters, infographics, social media creatives, readable text, or branded layouts
- The user is editing from reference images and needs identity, product, composition, or style preservation
- The user wants source frames, character sheets, product references, or storyboard frames for image-to-video workflows
- The user has unstable image outputs and needs diagnosis plus a cleaner second-pass prompt
When not to use
- The request is mainly about a different model or non-image workflow
- The user only wants final image generation, API integration, payment help, or account support
- The user asks for unsupported model settings, hidden system behavior, or official provider claims
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.
- 11d ago First seen · 194 lines · 84 tokens per session scan A 2614247e574d
gpt-image-2-prompt-architect is a skill published in the GitHub repository gpt-img-2/image3-prompt-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 84 tokens to every session and 1,623 once invoked, about $0.0004 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 skills, from other repositories
china-video-prompt-architect
Turn rough China AI video ideas into structured English or Chinese prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, reference-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for…
opensora-video-prompt-architect
Turn rough video ideas into structured OpenSora prompt packs, reference-aware motion instructions, shot plans, and focused debugging loops. Use for text-to-video, image-to-video, video-to-video, product clips, cinematic scenes, transitions, or multi-shot sequences; do not use for unrelated models, account support, or…
see-dance-2-video-prompt-architect
Turn rough video ideas into structured English or Chinese Seedance-oriented prompt packs, exact reference bindings, shot sequences, and focused debugging loops. Use for text-to-video, image-to-video, multimodal reference, product clips, cinematic scenes, transitions, or loops; do not use for account support, live…
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.