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 codex-curator/studiomcphub --skill studiogit clone --depth 1 https://github.com/codex-curator/studiomcphubWrote 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/codex-curator/studiomcphub/studio)<a href="https://agentmods.dev/skills/codex-curator/studiomcphub/studio"><img src="https://agentmods.dev/badge/skills/codex-curator/studiomcphub/studio/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/codex-curator/studiomcphub/studio"><img src="https://agentmods.dev/badge/skills/codex-curator/studiomcphub/studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low MCP Rug Pull · line 32 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
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 | $0.00073 | $0.00589 |
| Opus 5.5 | $0.00029 | $0.00236 |
| Sonnet 5.5 | $0.00015 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
studiomcphub-studio 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 1mo 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
StudioMCPHub Studio
Image to Retail in 90 seconds.
Drop an image, get back: transparent PNG, color palette, product mockups (6 products), CMYK print files, print-ready PDFs with bleed/crop marks, SVG vectors, invisible watermarks, AI-enriched metadata, and 4x ESRGAN upscales. All organized in a local DAM with HTML preview.
Quick Start
pip install studiomcphub-studio
studio init my-project && cd my-project
studio process artwork.png -c my-collection
studio preview my-collection
Pipeline Stages
| # | Stage | What it does | Free? |
|---|---|---|---|
| 1 | remove_bg | Transparent PNG (U2-Net) | Yes |
| 2 | palette | 6-color hex palette | Yes |
| 3 | resize | Fit to max dimensions | Yes |
| 4 | mockup | T-shirt, poster, canvas, phone, mug, tote | Yes |
| 5 | cmyk | CMYK @ 300 DPI for print | Yes |
| 6 | print_ready | PDF with bleed + crop marks | Yes |
| 7 | vectorize | SVG via vtracer | Yes |
| 8 | watermark | Invisible DCT watermark | Yes |
| 9 | enrich | AI metadata (Gemini) | 1-2 GCX |
| 10 | upscale | 4x ESRGAN | 1 GCX |
Configuration
Edit studio.json to customize stages, mockup products, print sizes, and more.
POD Export (Phase 2)
studio export my-collection --platform gooten
studio export my-collection --platform printful
studio export my-collection --platform printify
What ships with it
33 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.
- pyproject.toml 1.1 KB
- README.md 413 B
- studio.example.json 830 B
- studio/__init__.py 304 B runs code
- studio/__main__.py 74 B runs code
- studio/cli.py 7.1 KB runs code
- studio/client.py 3.5 KB runs code
- studio/config.py 2.0 KB runs code
- studio/connectors/__init__.py 700 B runs code
- studio/connectors/gooten.py 871 B runs code
- studio/connectors/printful.py 743 B runs code
- studio/connectors/printify.py 736 B runs code
- studio/dam.py 4.1 KB runs code
- studio/models.py 2.2 KB runs code
- studio/pipeline.py 3.2 KB runs code
- studio/preview.py 1.7 KB runs code
- studio/stages/__init__.py 2.5 KB runs code
- studio/stages/color_profile.py 1.1 KB runs code
- studio/stages/enrich.py 1.4 KB runs code
- studio/stages/mockup.py 1.6 KB runs code
- studio/stages/palette.py 1012 B runs code
- studio/stages/print_ready.py 2.1 KB runs code
- studio/stages/remove_bg.py 1.1 KB runs code
- studio/stages/resize.py 1.3 KB runs code
- studio/stages/upscale.py 1.2 KB runs code
- studio/stages/vectorize.py 1.0 KB runs code
- studio/stages/watermark.py 1.2 KB runs code
- studio/templates/gallery.html 4.9 KB
- tests/__init__.py 0 B runs code
- tests/conftest.py 1.7 KB runs code
- tests/test_client.py 1.2 KB runs code
- tests/test_dam.py 1.9 KB runs code
- tests/test_pipeline.py 2.6 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.
- 1mo ago First seen · 64 lines · 73 tokens per session scan A 2f63a5830e83
studiomcphub-studio is a skill published in the GitHub repository codex-curator/studiomcphub (7 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 589 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
asset-description-writer
Writes structured, searchable descriptions for digital assets — photos, videos, audio files, graphics, and documents — enabling accurate retrieval from a digital asset management (DAM) system or media archive.
meme-sticker
Turn one uploaded image into a complete 12-piece chat sticker pack by generating two 3x2 sticker sheets, extracting transparent PNGs, normalizing their canvases, and packaging the result as a ZIP. Use this skill whenever a user provides a photo and asks for chat stickers, reaction stickers, meme stickers, custom…
ai-ecommerce-expert-1688-ecommerce-content
A workflow for creating product images, listing content, and videos for 1688, a Chinese wholesale e-commerce marketplace. It uses IMIVA, an AI e-commerce content platform, to organize materials around listing, promotion, and sales goals.
ai-ecommerce-expert-gpt-image-2-ecommerce-image
A workflow for creating online-store images with GPT Image 2, including product retouching, new scenes, advertising visuals, and edits based on reference images. It organizes the request and sends it through the IMIVA service.
ai-ecommerce-expert-horizontal-16-9-tvc
A workflow for creating 16:9 commercial product videos, also called TVCs, for websites, events, YouTube, and horizontal advertising spaces. The 16:9 ratio is the widescreen format commonly used for video.
ecommerce-detail-page-generator
Turn product photos and a minimal brief into verified, platform-adapted e-commerce detail-page systems, including product fact review, visual analysis, localized copy, 6-10 module story planning, policy-aware text-free image generation or real-photo routing, deterministic Pillow typography, platform-sized slices…