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 tody-agent/affiliate-product --skill shopee-sellergit clone --depth 1 https://github.com/tody-agent/affiliate-productWrote 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/tody-agent/affiliate-product/shopee-seller)<a href="https://agentmods.dev/skills/tody-agent/affiliate-product/shopee-seller"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/shopee-seller/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/tody-agent/affiliate-product/shopee-seller"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/shopee-seller.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 | $0.00048 | $0.01090 |
| Opus 5.5 | $0.00019 | $0.00436 |
| Sonnet 5.5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
shopee-seller 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 2mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏪 Shopee Seller & Store Intelligence (shopee-seller)
Thuộc Plugin: shopee-research
Overview
shopee-seller là kỹ năng chuyên sâu để nghiên cứu và thẩm định chất lượng các Gian hàng / Nhà bán hàng trên Shopee (Shopee Mall, Shop Yêu Thích+):
- Store Profile Audit: Trích xuất toàn bộ chỉ số vận hành của Shop: Số lượng Follower, Số lượng sản phẩm đang bán, Đánh giá trung bình sao (4.x/5.0), Tỷ lệ phản hồi chat & tốc độ trả lời khách hàng, Thời gian hoạt động (năm tham gia).
- Shop Health Score (Chỉ số Sức khỏe Gian hàng): Thuật toán chấm điểm độ tin cậy của Shop từ 0 đến 100 điểm dựa trên 4 trụ cột: Chất lượng đánh giá (35đ), Dịch vụ CSKH (25đ), Danh hiệu Mall/Yêu thích (20đ), và Quy mô gian hàng (20đ).
- Voucher & Khuyến Mãi: Bóc tách danh sách mã giảm giá, voucher độc quyền của shop để đưa vào lời kêu gọi hành động (CTA) trong video tiếp thị liên kết.
- Top Best-Sellers: Thống kê danh sách các sản phẩm bán chạy nhất của gian hàng để tìm kiếm cơ hội bán kèm (Cross-sell / Bundle).
- Lưu trữ Cấu trúc SQLite: Lưu trực tiếp vào các bảng
shops,shop_vouchers,shop_rating_analyticstrong databaseproducts.db.
🎯 Khi Nào Sử Dụng (Triggers)
- Khi người dùng yêu cầu: "Research shop này trên Shopee", "Đánh giá gian hàng Ugreen có uy tín không", "Xem shop này có voucher gì và sản phẩm nào bán chạy nhất".
- Khi vừa chạy
shopee-searchvà cần thẩm định độ uy tín của các gian hàng đứng đầu kết quả tìm kiếm trước khi chọn làm tiếp thị liên kết. - Khi cần kiểm tra thông tin bảo hành, độ tin cậy để bổ sung vào kịch bản review.
🏗️ Quy Trình Thẩm Định 3 Bước
flowchart TD
A[Shop URL / Shop ID / Username] --> B[1. Store Metrics Extraction\nFollowers + Rating + Response Rate + Vouchers]
B --> C[2. AI Seller Health Calculation\nThang điểm 100 theo 4 trụ cột uy tín]
C --> D[3. Persist to SQLite & Link to Products\nLưu shops & shop_vouchers]
Bước 1: Trích xuất chỉ số gian hàng
python3 scripts/seller_auditor.py
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.
- 2mo ago First seen · 72 lines · 48 tokens per session scan A 32275696b1e2
shopee-seller is a skill published in the GitHub repository tody-agent/affiliate-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,090 once invoked, about $0.0002 per session on Opus 5.5. 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.
shopee-seller compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shopee-sellertody-agent/affiliate-product | Skill | 2 | 2mo ago | MIT | A | 48 | Claude Code, Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 4d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 867 | yesterday | MIT | A | 76 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | today | MIT | A | 53 | Claude Code, Codex |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | 2d ago | MIT | A | 111 | Claude Code |