Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/citedy/adclawnpx agentmods add skills/citedy/adclaw/ads-photoshootWrote 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/citedy/adclaw/ads-photoshoot)<a href="https://agentmods.dev/skills/citedy/adclaw/ads-photoshoot"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/ads-photoshoot/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/citedy/adclaw/ads-photoshoot"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/ads-photoshoot.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 | $0.00101 | $0.01959 |
| Opus 5 | $0.00051 | $0.00979 |
| Sonnet 5 | $0.00020 | $0.00392 |
| Haiku 4.5 | $0.00010 | $0.00196 |
Grade A, and why
ads-photoshoot 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ads Photoshoot: AI Product Photography
Transforms a product image or description into professional ad-ready photography in 5 distinct visual styles. Each style generates at two sizes: 1:1 (Meta/LinkedIn) and 9:16 (TikTok/Reels/Stories).
Quick Reference
| Command | What it does |
|---|---|
/ads photoshoot |
Interactive: ask for product + styles |
/ads photoshoot --styles studio floating |
Generate only selected styles |
/ads photoshoot --product shoe.jpg |
Start with a product image file |
/ads photoshoot --all-platforms |
Generate all 5 sizes per style |
Environment Setup
Requires banana-claude (v1.4.1+) with nanobanana-mcp configured.
Run /banana setup to configure API key and MCP.
Process
Step 1: Collect Product Information
Ask (combine into one message):
- Product image: Path to product image file (local) OR product URL OR text description
"Provide a product image path (e.g. ./product.jpg), a URL, or describe your product"
- Product description: What is it? Key features to highlight? (helps prompt quality)
- Styles to generate: Which of the 5 styles? (default: all 5)
- Studio, Floating, Ingredient, In Use, Lifestyle
- Target platforms: Which platforms will these run on?
- Determines output sizes (default: Meta + TikTok → 1:1 + 9:16)
Step 2: Load Brand Profile (Optional)
Check for brand-profile.json in the current directory.
If found, extract for style injection:
colors.primary→ inject into backgrounds and accent elementsaesthetic.mood_keywords→ inject as atmosphere descriptorstarget_audience→ use for Lifestyle and In Use contextimagery.forbidden→ exclude from all prompts
If not found, proceed with standard style templates.
Step 3: Verify banana-claude
Verify banana-claude is installed (run /banana setup to check). If not installed,
display setup instructions and exit.
Step 4: Construct Prompts per Style
For each selected style, build the prompt using the template + product description + brand DNA.
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 · 214 lines · 101 tokens per session scan A 8eedbca27e56
ads-photoshoot is a skill published in the GitHub repository citedy/adclaw (36 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,959 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
youtube
A YouTube integration for searching videos, reading video details, summarising subtitles, viewing subscriptions and liked videos, downloading videos, and monitoring channels for new uploads.
tts
A text-to-speech tool that turns written text into an audio message or an animated video circle with a robot avatar and waveform. It supports OpenAI voices and free multilingual voices from edge-tts.
image_gen
An image-generation tool that creates one picture from a written description using DALL-E 3.
skill-creator
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
weather
Get current weather and forecasts (no API key required).
github
Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.