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 alecs5am/ralphy --skill static-adsgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/static-ads)<a href="https://agentmods.dev/skills/alecs5am/ralphy/static-ads"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/static-ads.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.04462 |
| Opus 5 | $0.00040 | $0.02231 |
| Sonnet 5 | $0.00016 | $0.00892 |
| Haiku 4.5 | $0.00008 | $0.00446 |
Grade A, and why
static-ads scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Download each image using curl and save to brands/[brand-name]/brand-identity/product-images/ with a descriptive filename (e.g. electrolytes-sachet-front.jpg). How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Static Ads
Recreates a winning ad format with the brand's own products and copy.
Output saved to ./brands/[brand-name]/static-ads/[output-name]/.
Step 1 — Select brand Scan ./brands/ for subfolders that contain a brand-identity/visual-guidelines.md file.
- One brand found: use it automatically and confirm: "Using brand: [name]"
- Multiple brands found: list them and ask which to use
- None found: tell the user to run /brand first
Step 2 — Upload ad format reference Create the shared ad references folder if it doesn't exist:
bash
mkdir -p brands/[brand-name]/static-ads/ad-references Ask:
"Drop the ad format you want to recreate into: brands/[brand-name]/static-ads/ad-references/ Name it descriptively — e.g. calling-screen.jpg, iMessage-format.png. Let me know the filename when it's in."
Wait for the user to confirm. Then read the image from disk using the Read tool.
Analyse it internally. Do not share the analysis or prompt template with the user. Extract:
- Ad format type — e.g. iMessage conversation, countdown urgency, ingredient spotlight, testimonial card, before/after, price reveal
- Layout structure — background colour/texture, sections from top to bottom, visual hierarchy, whitespace logic
- Typography treatment — font weights, sizes, capitalisation, colour usage per text role
- Copy framework — every text slot that exists: its role (headline, subheadline, body, message bubble, CTA, disclaimer, badge, etc.), its tone (casual, urgent, clinical, social), and its position
- Product placement — how the product appears: size, position, angle, crop, lighting treatment, whether it floats or sits in context
- Brand signals — logo placement, colour palette usage, any visual motifs
Extract layout zones — express each content zone as a fraction of total frame height (0.0 = top edge, 1.0 = bottom edge). Use these zone names where applicable:
- text_zone — where headline and sub-headline sit
- product_zone — where the product is placed
- button_zone — where the CTA button sits
- disclaimer_zone — where the disclaimer text sits
Example for a calling-screen format:
json
"layout_zones": { "text_zone": {"top": 0.10, "bottom": 0.35}, "product_zone": {"top": 0.40, "bottom": 0.77}, "button_zone": {"top": 0.81, "bottom": 0.91}, "disclaimer_zone": {"top": 0.91, "bottom": 0.97} } These zones are used to generate a brand-neutral wireframe at the target aspect ratio. The wireframe is what gets passed to GPT-image-2 as Image 1 — not the original ad. This eliminates color, typeface, and style contamination from the reference, and there is no aspect ratio conflict regardless of the source format.
Construct a prompt template using the zone-based pattern described in Step 7. Store it internally. Do not show it to the user.
Step 3 — Select product(s) and copy variation count Ask in one message:
"Which product would you like to feature? And how many copy variations do you want?"
Finding product images — always follow this order:
- Check local folders first:
- brands/[brand-name]/brand-identity/product-images/
- brands/[brand-name]/brand-identity/uploads/ (if it exists)
- If no matching images found locally — fetch from the brand's website:
Check products.json for a matching product_url. If found, fetch it. If not found, use WebFetch on the brand's main site (from visual-guidelines.md or products.json domain) to search for the product — e.g. fetch [brand-domain]/products or [brand-domain]/collections/all. If multiple products match the name (e.g. several flavours or sizes), list them and ask the user which to use before proceeding. Once the correct product page is identified, WebFetch it and extract all product image URLs. Download each image using curl and save to brands/[brand-name]/brand-identity/product-images/ with a descriptive filename (e.g. electrolytes-sachet-front.jpg). Add the product to products.json if it isn't already there. 3. If images still can't be retrieved (page blocked, images not accessible, wrong product): ask the user to drop images into brands/[brand-name]/brand-identity/product-images/.
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.
- 3d ago First seen · 269 lines · 80 tokens per session scan A 7bddbb17143f
static-ads is a skill published in the GitHub repository alecs5am/ralphy (131 stars, last pushed 12d ago), licensed Apache-2.0. It adds 80 tokens to every session and 4,462 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
molecule-visualization
Publication-quality molecular visualization. 2D structure drawings (PNG/SVG), molecule grids with property annotations, scaffold highlighting, protein-ligand interaction diagrams, and interactive 3D views.
ppt-orchestrator
A dispatcher for creating presentations, slide decks, long images, and weekly reports. It chooses a visual style and output format, then sends the work to a more specialised add-on.
zhongguose-html-skill
An HTML-only presentation system using traditional Chinese colours and Chinese-style visual design. It helps organise source material into a report structure and produces a self-contained HTML file with its assets.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
wechat-delivery
A workflow for preparing WeChat Official Account articles, images, covers, and publishing files in Chinese. WeChat Official Accounts are channels used by organizations to publish articles to followers.
html-ppt-viewer
A simple HTML viewer that presents a set of existing images like a slide deck. It includes a side panel, large image display, page controls, and keyboard navigation, but does not create the images.