agentmods.dev

haravan-mcp

A Vietnamese-language skill for analyzing and operating Haravan online stores. Haravan is an e-commerce platform for managing sales, orders, stock, customers, and products.

In plain words
What is it for?
Analyzing revenue, orders, inventory, customers, products, cash-on-delivery payments, customer groups, catalogs, and store scorecards.
Why use it?
It tells the agent how to use store data, summarize it, and suggest actions without guessing or inventing figures.

Skill for Claude CodeCodex

18 4mo ago A scan 93 tokens original Apache-2.0
View the source file pluginmd/Haravan-MCP
Install

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.

agentmods
npx agentmods add skills/pluginmd/haravan-mcp/haravan-mcp
Any agent
npx skills add pluginmd/Haravan-MCP --skill haravan-mcp
Clone the repo
git clone --depth 1 https://github.com/pluginmd/Haravan-MCP

Made for: Claude Code, Codex.

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,495 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00093 $0.12495
Opus 5 $0.00046 $0.06247
Sonnet 5 $0.00019 $0.02499
Haiku 4.5 $0.00009 $0.01249

Measured 3d ago against content hash d5e78c1d29d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

haravan-mcp 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 3d 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.

claudeskill/haravan-mcp/SKILL.md · 963 lines

How it starts

The opening of the file, as written. The whole thing — 963 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Haravan MCP — Bộ Não Phân Tích & Vận Hành Cửa Hàng E-commerce

Bạn là chuyên gia phân tích và vận hành e-commerce Haravan. Bạn sử dụng Haravan MCP tools để trả lời câu hỏi bằng data thực, không bao giờ suy đoán hay bịa số. Mọi insight phải kèm con số cụ thể và hành động thực thi được ngay.

PHẦN 1: QUY TẮC BẮT BUỘC

Quy tắc #1 — Smart Tools ưu tiên, Base Tools cho detail/action

  • hrv_* tools tự xử lý pagination bên trong MCP server, trả summary gọn (~200–800 tokens)
  • TUYỆT ĐỐI KHÔNG gọi haravan_orders_list rồi tự loop page=1, page=2... để đếm hay tổng hợp
  • TUYỆT ĐỐI KHÔNG gọi detail tool nhiều lần chỉ để "đếm" hay "tính tổng"
  • TUYỆT ĐỐI KHÔNG gọi cùng 1 tool 2 lần với cùng params trong cùng một phiên trả lời
  • Aggregation đơn giản (group by kênh, filter lý do hủy, tính tỷ lệ) → BẠN tự làm từ data smart tool đã trả về

Quy tắc #2 — Gọi SONG SONG tối đa khi có thể

  • Các hrv_* tools không có dependency với nhau → gọi đồng thời trong cùng một bước
  • Giới hạn cứng: Tối đa 6 tool calls cho bất kỳ câu hỏi nào
  • Nếu logic cần >6 calls → đang thiết kế sai, cần dùng smart aggregation tool thay thế
  • Gọi song song = tiết kiệm 60–70% thời gian chờ so với gọi tuần tự

Quy tắc #3 — LUÔN truyền date range chính xác

  • Mọi tool liên quan thời gian BẮT BUỘC có date_from và date_to (định dạng ISO 8601: YYYY-MM-DD)
  • Nếu người dùng nói "tuần này" → date_from = thứ Hai tuần này, date_to = hôm nay
  • Nếu người dùng nói "tháng 3" → date_from = 2026-03-01, date_to = 2026-03-31
  • Nếu người dùng nói "hôm nay" → date_from = date_to = today
  • Không truyền date → server dùng default 30 ngày — có thể sai kỳ vọng người dùng

Quy tắc #4 — XÁC NHẬN TRƯỚC mọi write action

  • Mọi thao tác tạo / sửa / xóa: hiển thị preview đầy đủ → đợi người dùng xác nhận → mới thực hiện
  • Preview phải bao gồm: resource bị ảnh hưởng, giá trị hiện tại, giá trị sẽ thay đổi
  • Batch >5 items: liệt kê rõ từng item trước khi hỏi xác nhận
  • Hủy đơn hàng: luôn hỏi lý do (customer/inventory/fraud/declined/other) để truyền đúng vào API

Read the full file on GitHub · 963 lines

Files

What ships with it

5 files 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.

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.

  1. 3d ago First seen · 963 lines · 93 tokens per session scan A d5e78c1d29d2

Subscribe to this mod's changes

haravan-mcp is a skill published in the GitHub repository pluginmd/Haravan-MCP (18 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 12,495 once invoked, about $0.0005 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 2026-08-30.

Analytics and metricsE-commerce
Related

Other skills, from other repositories

cloudflare-registrar

Cloudflare Registrar: domain availability, prices, registration via mcporter.

steipete/agent-scripts · 20 tokens

etsy-category-listing

Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…

browser-act/skills · 209 tokens

amazon-reviews-api-skill

This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…

browser-act/skills · 124 tokens

amazon-competitor-analyzer

Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.

browser-act/skills · 48 tokens

shopify-functions

Shopify Functions allow developers to customize the backend logic that powers parts of Shopify. Available APIs: Discount, Cart and Checkout Validation, Cart Transform, Pickup Point Delivery Option Generator, Delivery Customization, Fulfillment Constraints, Local Pickup Delivery Option Generator, Order Routing Location…

Shopify/Shopify-AI-Toolkit · 61 tokens

shopify-shopifyql

Answer a merchant's analytics and reporting questions with ShopifyQL — Shopify's query language for aggregated store metrics that the Admin GraphQL API cannot compute. Choose this (not admin) whenever the ask is for numbers, totals, trends, or breakdowns rather than fetching or mutating individual records: including…

Shopify/Shopify-AI-Toolkit · 216 tokens