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 FoneClaw-AI/foneclaw-android --skill shoppinggit clone --depth 1 https://github.com/FoneClaw-AI/foneclaw-androidWrote 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/foneclaw-ai/foneclaw-android/shopping)<a href="https://agentmods.dev/skills/foneclaw-ai/foneclaw-android/shopping"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/shopping.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 | $0.00012 | $0.00401 |
| Opus 5 | $0.00006 | $0.00200 |
| Sonnet 5 | $0.00002 | $0.00080 |
| Haiku 4.5 | $0.00001 | $0.00040 |
Grade A, and why
shopping 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 7d 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
Shopping Price Comparison
Use this skill when the user wants to buy a product, compare prices, find the lowest price, compare Shopee and momo, or evaluate whether a product offer is worth buying.
Tool Policy
- Prefer
shopping_comparefor shopping comparison requests. - Use the user's product name, brand, model, spec, size, color, storage, version, or URL as the query.
- If the user's product identity is ambiguous, ask for the missing model or spec before comparing.
- If the user specifies a platform, pass that platform in
platforms; otherwise compare Shopee and momo. - Treat tool output as public web-search evidence, not as a guaranteed official live price feed.
- If the candidate page cannot be fetched, still use the search result as weak evidence and say it needs confirmation.
Answer Policy
- Answer in the user's language.
- Always include the data refresh time from the tool output.
- Distinguish lowest extracted price from the safest purchase recommendation.
- Do not recommend only by the lowest price.
- Compare product spec match, shipping fee, coupon conditions, seller risk, delivery time, warranty, and after-sales risk when evidence is available.
- Mark whether a result appears to be organic, ad, sponsored, user specified, or unknown.
- If ad or sponsored status is unknown, say it is unknown instead of assuming it is organic.
- Explain when live price, stock, shipping, and coupon details still need final confirmation on the seller page.
- If the lowest-price item has unclear spec, low seller trust, missing warranty, suspicious title, or unclear shipping/coupon terms, provide a safer alternative.
Price Monitoring
If the user asks to monitor a price or receive a reminder, explain that the current implementation can compare current web-search evidence but does not yet include a background price monitor.
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.
- 7d ago First seen · 35 lines · 12 tokens per session scan A cafa7bda9002
shopping is a skill published in the GitHub repository FoneClaw-AI/foneclaw-android (6 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 401 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
qa
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate this landing page").…
domain-hunter
Search domains, compare prices, find promo codes, get purchase recommendations. Use when user wants to buy a domain, check domain prices, find domain deals, compare registrars, or search for .ai/.com domains.
product-image-processor
Download, resize, and remove backgrounds from product images at scale. Use when the user asks to "process product images", batch-download images from the schedule, strip backgrounds, or standardize product photos.
product-match
Find visually or functionally similar products from an image, name, or description. Use when the user asks to "find something like this", match a product from a photo, or source alternates to a given item.
product-pair
Suggest complementary products that pair well with a given item — side tables for sofas, task lights for desks, etc. Use when the user asks "what goes with" a product, wants coordinating pieces, or asks to complete a furniture grouping.
product-spec-bulk-fetch
Extract structured FF&E specs from a list of product URLs into a schedule. Use to pull or bulk-import product-page data; not for PDF catalogs.