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 tdimino/claude-code-minoan --skill gpt-ateliergit clone --depth 1 https://github.com/tdimino/claude-code-minoanWrote 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/tdimino/claude-code-minoan/gpt-atelier)<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/gpt-atelier"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/gpt-atelier/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/tdimino/claude-code-minoan/gpt-atelier"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/gpt-atelier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.02235 |
| Opus 5 | $0.00063 | $0.01118 |
| Sonnet 5 | $0.00025 | $0.00447 |
| Haiku 4.5 | $0.00013 | $0.00224 |
Grade A, and why
gpt-atelier 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT Atelier
OpenAI GPT Image generation and editing. Wraps both the Image API (one-shot) and Responses API (multi-turn conversational) with 6 scripts covering generate, edit, compose, converse, stream, and test workflows.
Prerequisite: OPENAI_API_KEY environment variable.
Models
| Flag | Model | Strengths |
|---|---|---|
| (default) | gpt-image-2 |
Reasoning-based, ~99% text rendering, up to 8 consistent images, 4K, streaming |
--fast |
gpt-image-1.5 |
Region-aware editing, 4x faster, cheaper |
--mini |
gpt-image-1-mini |
Cheapest ($0.006/image low quality) |
Quick Start
# Test connectivity
python3 scripts/test_connection.py --check-models
# Generate an image
python3 scripts/generate_image.py "A Minoan bull-leaper under golden light"
# Compare models side-by-side (HTML page)
python3 scripts/compare_models.py "A bronze seal stamp in Minoan style" --all --open
# Edit with mask
python3 scripts/edit_image.py "Replace the sky with a dramatic sunset" photo.png --mask sky_mask.png
# Compose from references
python3 scripts/compose_images.py "Create a gift basket containing these items" item1.png item2.png item3.png
# Multi-turn editing session
python3 scripts/converse_image.py
# Streaming with partial images
python3 scripts/stream_image.py "An ancient fresco being restored" --partials 3
Image API scripts share: --output DIR, --filename NAME, --quality low|medium|high, --format png|jpeg|webp, --fast, --mini. converse_image.py uses --orchestrator instead of --fast/--mini.
Core Workflows
1. Text-to-Image Generation
python3 scripts/generate_image.py "prompt" [options]
| Option | Default | Description |
|---|---|---|
--size |
auto | WxH or preset: square, landscape, portrait, wide, 2k, 4k, 4k-portrait |
--quality |
high | low, medium, high, auto |
--n |
1 | Number of images (1-8) |
--format |
png | png, jpeg (faster), webp |
--compression |
— | 0-100 for jpeg/webp |
--background |
— | opaque, transparent, auto |
--moderation |
auto | auto, low |
What ships with it
13 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.
- README.md 5.0 KB
- references/api-reference.md 4.0 KB
- references/compare-models-reference.md 2.7 KB
- references/prompting-guide.md 6.5 KB
- references/troubleshooting.md 2.2 KB
- scripts/compare_models.py 11 KB runs code
- scripts/compose_images.py 3.0 KB runs code
- scripts/converse_image.py 7.7 KB runs code
- scripts/edit_image.py 4.9 KB runs code
- scripts/generate_image.py 2.8 KB runs code
- scripts/openai_images.py 9.5 KB runs code
- scripts/stream_image.py 4.7 KB runs code
- scripts/test_connection.py 5.3 KB runs code
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 · 231 lines · 126 tokens per session scan A a77ed11bd405
gpt-atelier is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 2,235 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
media-processing
Ingest and process media files (video, audio, image).
fish-audio
Generate expressive audio clips using Fish Audio S2 TTS with bracket emotion tags. Record voice memos, narration, audio messages, or any spoken content.
voice-setup
Complete voice configuration in chat - desktop Talk and PTT shortcuts, microphone permissions, ElevenLabs/Deepgram TTS, and troubleshooting.