What is affiliate-product AGENTS.md?

A set of operating instructions for an affiliate-marketplace research project covering Shopee, TikTok Shop, and video analysis.

It helps research products, group prices, score opportunities, inspect product variations and reviews, and prepare conversion-focused scripts or handoffs.

It tells the coding agent how to run the research pipeline from product discovery through scoring and reporting without stopping for repeated approval.

How tody-agent/affiliate-product configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to tody-agent/affiliate-product. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tody-agent/affiliate-product/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/tody-agent/affiliate-product

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tody-agent/affiliate-product/agents-md/github.svg)](https://agentmods.dev/instructions/tody-agent/affiliate-product/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tody-agent/affiliate-product/agents-md"><img src="https://agentmods.dev/badge/instructions/tody-agent/affiliate-product/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tody-agent/affiliate-product/agents-md"><img src="https://agentmods.dev/badge/instructions/tody-agent/affiliate-product/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 769 This file is loaded in full into every session.

When invoked 769 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00769	$0.00769
Opus 5.5	$0.00308	$0.00308
Sonnet 5.5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 2mo ago against content hash 7908f5316de8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

affiliate-product AGENTS.md 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.

AGENTS.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Affiliate Marketplace & Product Intelligence — Autonomous Execution Rules

⚡ Zero Confirmation Fatigue & Pipeline Autonomy (MANDATORY)

Autonomous End-to-End Execution:
- Khi người dùng yêu cầu nghiên cứu tiếp thị liên kết (Affiliate Research), tìm sản phẩm win, thẩm định gian hàng, hoặc phân tích Hotlist:
  - TỰ ĐỘNG THỰC HIỆN TRỌN VẸN PIPELINE: Tìm kiếm → Phân cụm giá → Chấm điểm Win Score → Trích xuất biến thể SKU & Review hạt giống → Tạo kịch bản CRO / Handoff.
  - TUYỆT ĐỐI KHÔNG DỪNG LẠI XIN PHÉP GIỮA CHỪNG: Không hỏi những câu như "Tôi đã tìm thấy 5 sản phẩm, bạn muốn tôi cào chi tiết sản phẩm nào?".
  - Tự động chọn Top 1-3 sản phẩm có điểm Win cao nhất để hoàn tất quy trình và báo cáo kết quả trọn gói.
Phân Định Trách Nhiệm Với Dự Án /Volumes/Agency/Research:
- Products (/Volumes/Agency/Products): Tập trung nghiên cứu sàn TMĐT (Shopee, TikTok Shop, FastMoss Hotlist, Seller Audit, SKU Variants, Reviews hạt giống, Win Score).
- Research (/Volumes/Agency/Research): Chịu trách nhiệm bóc tách sâu video media (MLX Whisper STT trên Apple Silicon, 6 keyframes CRO, nhận diện 12 Hook Archetypes, lưu trữ SQLite FTS5 và xuất Obsidian Markdown Vault).
- VideoFactory (/Volumes/Agency/VideoFactory): Chịu trách nhiệm dựng hình, tổng hợp giọng nói OmniVoice và render video thành phẩm.
Smart E-Commerce Defaults (Mặc định Thông minh):
- Khu vực: Vietnam (VN).
- Khung thời gian: 28-30 ngày gần nhất (doanh số 28d GMV).
- Phân khúc giá vàng: 150.000₫ – 500.000₫ (Impulse Buy Sweetspot).
- Định dạng Video: 45s (6 cảnh CRO) chuẩn VideoFactory (AIEV).
- Graceful Fallback: Nếu FastMoss offline, tự động chuyển hướng sử dụng dữ liệu trực tiếp từ Shopee/TikTok Shop.
Không Tạo Menu Khảo Sát Cuối Báo Cáo:
- Không chèn các câu hỏi dạng trắc nghiệm "Bạn muốn làm gì tiếp theo? 1. ... 2. ... 3. ..." ở cuối mỗi câu trả lời. Trả về kết quả hoàn chỉnh, súc tích và có thể hành động được ngay.

Read the full file on GitHub · 30 lines

Changes

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 · 30 lines · 769 tokens per session scan A 7908f5316de8

Subscribe to this mod's changes

affiliate-product AGENTS.md is an instructions file published in the GitHub repository tody-agent/affiliate-product (2 stars, last pushed 2mo ago), licensed MIT. It adds 769 tokens to every session, about $0.0031 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.

E-commerce Research

affiliate-product AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
affiliate-product AGENTS.mdtody-agent/affiliate-product	Instructions file	2	2mo ago	MIT	A	769	Codex, OpenCode
vibetags com-example-service-OrderService.instructions.mdPIsberg/vibetags	Instructions file	25	today	MIT	A	553	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot

affiliate-product: Instructions file for Codex