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 s2leh/deal-watcher-ai-agent --skill amazon-price-trackergit clone --depth 1 https://github.com/s2leh/deal-watcher-ai-agentWrote 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/s2leh/deal-watcher-ai-agent/amazon-price-tracker)<a href="https://agentmods.dev/skills/s2leh/deal-watcher-ai-agent/amazon-price-tracker"><img src="https://agentmods.dev/badge/skills/s2leh/deal-watcher-ai-agent/amazon-price-tracker/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/s2leh/deal-watcher-ai-agent/amazon-price-tracker"><img src="https://agentmods.dev/badge/skills/s2leh/deal-watcher-ai-agent/amazon-price-tracker.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.00294 |
| Opus 5 | $0.00011 | $0.00147 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
amazon-price-tracker 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 44 lines · 22 tokens per session scan A b0c4acfad5d2
amazon-price-tracker is a skill published in the GitHub repository s2leh/deal-watcher-ai-agent (0 stars, last pushed 1mo ago), with no licence file. It adds 22 tokens to every session and 294 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
marketing-knowledge-commerce-strategist
A strategy guide for selling educational and expert knowledge through Chinese paid-content platforms. It covers product design, pricing, user operations, personal-brand building, referrals, and business data.
marketing-china-ecommerce-operator
A China e-commerce operations specialist covering Taobao, Tmall, Pinduoduo, and JD.com.
marketing-cross-border-ecommerce
An operations guide for selling across international e-commerce platforms. It covers platform rules, traffic sources, and adapting products and marketing to local markets for Chinese sellers.
marketing-livestream-commerce-coach
A coach for livestream shopping, where presenters sell products during live video broadcasts. It covers scripts, product selection, traffic sources, conversion tactics, and improving a livestream using live data.
marketing-private-domain-operator
An operations guide for building a private customer network with WeCom, Tencent’s business messaging platform. It covers customer groups, a mini-program shop, customer lifecycle management, and sales funnels.
marketing-ecommerce-operator
An operations guide for major Chinese e-commerce platforms, including Taobao, Tmall, Pinduoduo, and JD.com. It covers store management, product listings, live selling, major promotions, and platform-specific tactics.