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 aff-winning-validatorgit 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/aff-winning-validator)<a href="https://agentmods.dev/skills/tody-agent/affiliate-product/aff-winning-validator"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/aff-winning-validator/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/aff-winning-validator"><img src="https://agentmods.dev/badge/skills/tody-agent/affiliate-product/aff-winning-validator.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 | $0.00053 | $0.00528 |
| Opus 5.5 | $0.00021 | $0.00211 |
| Sonnet 5.5 | $0.00011 | $0.00106 |
| Haiku 4.5 | $0.00005 | $0.00053 |
Grade A, and why
aff-winning-validator 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.
What it actually says
🏆 Affiliate Winning Product Validator (aff-winning-validator)
Thuộc Plugin: afflite-master-connector
Overview
aff-winning-validator là bộ não thẩm định sản phẩm Win đa sàn, kết hợp đối chứng chéo giữa Shopee PDP + TikTok Shop PDP + (Tùy chọn) FastMoss Analytics để chấm điểm Affiliate Win Index (0-100đ):
- 6 Trụ Cột Đánh Giá:
- Tốc độ bán hàng (Sales Velocity)
- Biên độ hoa hồng (Commission Yield)
- Hiệu quả quảng cáo video (Ad ROAS Health)
- Độ rõ ràng SKU bán chạy (SKU Clarity)
- Điểm thưởng phân tán KOC (Creator Dispersion Bonus)
- Điểm phạt tự bán (Self-Selling Dominance Penalty)
- Cơ Chế Kháng Phụ Thuộc (Graceful Degradation):
- Khi có dữ liệu FastMoss: Tích hợp phân tích ROAS video, đồ thị mua kèm và thị phần biến thể bán chạy.
- Khi KHÔNG có FastMoss (hết hạn / không dùng FastMoss): Tự động đánh giá dựa trên các chỉ số e-commerce gốc (lượt bán, đánh giá review, hoa hồng, uy tín shop) mà không bị gián đoạn quy trình.
- Xác Định Mẫu Mã Tâm Điểm: Đề xuất chính xác SKU bán chạy nhất cho Scene 1 & Scene 3 của VideoFactory.
- Trích Xuất Công Thức Hook AI: Gợi ý các kịch bản Hook chuyển đổi cao dựa trên Top video bán chạy hoặc Pain Points của người mua thực tế.
💻 Cách Sử Dụng
# Thẩm định sản phẩm Win bất kỳ (Shopee, TikTok Shop hoặc FastMoss ID/URL):
afflite validate "1736384311671555227"
afflite validate "tiktok_prod_1729463065317050819"
afflite validate "giá đỡ laptop"
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 · 35 lines · 53 tokens per session scan A fcf3b8affbef
aff-winning-validator is a skill published in the GitHub repository tody-agent/affiliate-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 528 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.
aff-winning-validator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aff-winning-validatortody-agent/affiliate-product | Skill | 2 | 2mo ago | MIT | A | 53 | 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 |