Borrowing it
Nothing to install: this file belongs to pnsk-lab/saizeriya. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pnsk-lab/saizeriya/main/.agents/menu-image-assets/SKILL.mdgit clone --depth 1 https://github.com/pnsk-lab/saizeriyaWrote 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/pnsk-lab/saizeriya/menu-image-assets)<a href="https://agentmods.dev/skills/pnsk-lab/saizeriya/menu-image-assets"><img src="https://agentmods.dev/badge/skills/pnsk-lab/saizeriya/menu-image-assets/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/pnsk-lab/saizeriya/menu-image-assets"><img src="https://agentmods.dev/badge/skills/pnsk-lab/saizeriya/menu-image-assets.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 | $0.00097 | $0.01206 |
| Opus 5 | $0.00048 | $0.00603 |
| Sonnet 5 | $0.00019 | $0.00241 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
menu-image-assets 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Menu Image Assets
Generate menu thumbnails by asking the image generation tool for 4x4 contact sheets, then split each sheet into per-menu-item images.
Outputs
- Final item images:
apps/betterzeriya/src/lib/assets/image/{code}.webp - UI references:
apps/betterzeriya/src/routes/sessions/[id]/+page.svelteloads images withimport.meta.glob('../../../lib/assets/image/*.webp', { eager: true, query: '?url', import: 'default' }) - Menu data: keep
apps/betterzeriya/src/lib/assets/data/menu.jsonfree of generated public URLs; useimageUrlonly for explicit external/official image URLs. - Temporary sheet files:
tmp/menu-image-sheets/sheet-001.webp, etc.
Do not reference images directly from $CODEX_HOME/generated_images. Copy or convert them into the workspace first.
Workflow
- Read
apps/betterzeriya/src/lib/assets/data/menu.json. - Chunk menu entries into groups of 16 in file order.
- For each chunk, call the built-in image generation tool once with the prompt template below.
- Find the newly generated files under
$CODEX_HOME/generated_images/<thread-id>/. - Copy or convert the generated sheets to
tmp/menu-image-sheets/sheet-001.webp,sheet-002.webp, and so on in generation order. - Split every sheet into a 4x4 grid in left-to-right, top-to-bottom order.
- Save each crop as
apps/betterzeriya/src/lib/assets/image/{code}.webp, preferably 512x512 WebP. - Ensure the UI maps each menu
codeto its generated asset throughimport.meta.glob. - Run
bun check:fixandbun run test.
Prompt Template
Use this prompt once per 16-item chunk. Normalize half-width kana in menu names with NFKC before inserting them.
Create one square contact-sheet image divided into an exact 4x4 grid of equal square cells.
Each cell is a realistic, appetizing food photo for one menu item from a generic Japanese casual Italian family restaurant.
Order is strict: fill the grid left-to-right across the top row, then the second row, third row, and bottom row.
Menu items:
1. row 1, column 1: <item 1 name>
2. row 1, column 2: <item 2 name>
3. row 1, column 3: <item 3 name>
4. row 1, column 4: <item 4 name>
5. row 2, column 1: <item 5 name>
6. row 2, column 2: <item 6 name>
7. row 2, column 3: <item 7 name>
8. row 2, column 4: <item 8 name>
9. row 3, column 1: <item 9 name>
10. row 3, column 2: <item 10 name>
11. row 3, column 3: <item 11 name>
12. row 3, column 4: <item 12 name>
13. row 4, column 1: <item 13 name>
14. row 4, column 2: <item 14 name>
15. row 4, column 3: <item 15 name>
16. row 4, column 4: <item 16 name>
Style: clean menu photography, centered dish, natural restaurant table lighting, consistent camera angle, realistic plating, no people.
Layout: 4 columns by 4 rows, equal cell sizes, each dish fully contained in its own cell with enough padding for later cropping.
Constraints: no text, no labels, no numbers, no logos, no watermarks, no brand marks, no trademarks, no restaurant signage, no mascots, no Saizeriya branding.
For any empty unused cell, leave the cell as a plain neutral tabletop with no dish and no text.
What ships with it
1 file 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.
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.
- 9d ago First seen · 88 lines · 0 tokens per session scan A e76f54f27631
menu-image-assets is a skill published in the GitHub repository pnsk-lab/saizeriya (348 stars, last pushed 3mo ago), licensed MIT. It adds 97 tokens to every session and 1,206 once invoked, about $0.0005 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
beat-sync-reel
Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.
byted-livesaas-master
A control tool for managing business livestreams, including rooms, comments, viewers, product cards, coupons, and live-session settings.
byted-ind-ecom-product-video-prompt
A structured prompt-writing guide for creating e-commerce product videos with Seedance 2.0. It turns one or more product images into a product showcase script using scene settings, timed shots, and output constraints.
tiktok-shop-branding
Brand building and positioning on TikTok Shop. Brand identity development, content pillars, community engagement, brand storytelling, and authenticity strategies. Use when the user asks about TikTok branding, brand building, brand identity, or brand positioning on TikTok.
tiktok-shop-content-strategy
TikTok Shop content creation strategy and planning. Trending formats, viral hooks, product showcasing, hashtag strategy, and content calendar development. Use when the user asks about TikTok content strategy, viral content creation, TikTok marketing, or content planning.
amazon-listing-images
Amazon product listing image strategy and optimization. Comprehensive shot planning, infographic design, lifestyle photography, mobile optimization, and conversion-focused visual content. Use when the user asks about Amazon images, product photography, visual optimization, or listing conversion.