Borrowing it
Nothing to install: this file belongs to minwoo19930301/korea-ecommerce-integrated-channel-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/minwoo19930301/korea-ecommerce-integrated-channel-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/minwoo19930301/korea-ecommerce-integrated-channel-mcpWrote 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/instructions/minwoo19930301/korea-ecommerce-integrated-channel-mcp/agents-md)<a href="https://agentmods.dev/instructions/minwoo19930301/korea-ecommerce-integrated-channel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/minwoo19930301/korea-ecommerce-integrated-channel-mcp/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.
<a href="https://agentmods.dev/instructions/minwoo19930301/korea-ecommerce-integrated-channel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/minwoo19930301/korea-ecommerce-integrated-channel-mcp/agents-md.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 | $0.01345 | $0.01345 |
| Opus 5 | $0.00673 | $0.00673 |
| Sonnet 5 | $0.00269 | $0.00269 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
korea-ecommerce-integrated-channel-mcp 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 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.
This is a copy
100% identical to korea-ecommerce-integrated-channel-mcp AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the technical operating guide for coding agents working in this repository. Keep the root README focused on the seller's problem, supported channels, and the shortest path to a preview.
Project identity
- Product name:
Korea E-commerce Integrated Channel MCP - Repository and distribution:
korea-ecommerce-integrated-channel-mcp - Python package:
korea_ecommerce_mcp - Console command:
korea-ecommerce-integrated-channel-mcp - Environment prefix:
KEIC_ - MCP serverInfo name:
Korea E-commerce Integrated Channel MCP
Do not use the names of commercial multi-channel integration products in code, documentation, tests, examples, commit messages, or repository metadata. Marketplace names are allowed where they identify an actual adapter.
Purpose and non-goals
The server accepts one seller-owned product record and coordinates product operations across SmartStore, Coupang, 11st, and ESM. It is local-first and preserves account-specific category, notice, address, delivery, and option fields in reviewed channel profiles.
It does not infer seller policy identifiers, scrape seller-center UIs, store credentials in profiles, or promise a distributed transaction across marketplaces.
Source layout
src/korea_ecommerce_mcp/models.py: canonical product and MCP command/result modelssrc/korea_ecommerce_mcp/server.py: FastMCP tool registrationsrc/korea_ecommerce_mcp/service.py: preview, approval, SKU locking, fan-out, and reconciliation rulessrc/korea_ecommerce_mcp/store.py: SQLite products, channel mappings, jobs, and completed idempotency resultssrc/korea_ecommerce_mcp/templates.py: safe local profile loading and placeholder renderingsrc/korea_ecommerce_mcp/adapters/: marketplace authentication and HTTP contractsprofiles/: reviewed channel payload templates; never put credentials heretests/: unit, adapter-contract, safety, persistence, and stdio MCP tests
Core invariants
MasterProduct.skuis the internal identity. A channel mapping binds that SKU to one durable external product ID.- Update, stop, resume, and delete use only the stored mapping.
expected_external_idsis an assertion and cannot bootstrap or override a mapping. - A create call skips channels that already have a mapping, so a partial publish can be retried with a new key without recreating successful channels.
- Mutations for the same SKU are serialized within one process.
- Fan-out is concurrent across selected channels but is not transactional. Record and return every channel result.
- A successful create response without a durable external ID is uncertain, not successful. Do not create a mapping and require reconciliation before retry.
- Do not automatically retry an external mutation after a timeout or ambiguous response.
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 · 121 lines · 1,345 tokens per session scan A f9f05dd0c137
korea-ecommerce-integrated-channel-mcp AGENTS.md is an instructions file published in the GitHub repository minwoo19930301/korea-ecommerce-integrated-channel-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,345 tokens to every session, about $0.0067 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to korea-ecommerce-integrated-channel-mcp AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).