Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add modoro-digital/VietNam-Business-Builder/plugin install business-builderWrote 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/modoro-digital/vietnam-business-builder/bb-customer)<a href="https://agentmods.dev/skills/modoro-digital/vietnam-business-builder/bb-customer"><img src="https://agentmods.dev/badge/skills/modoro-digital/vietnam-business-builder/bb-customer/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/modoro-digital/vietnam-business-builder/bb-customer"><img src="https://agentmods.dev/badge/skills/modoro-digital/vietnam-business-builder/bb-customer.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 | $0.00100 | $0.01776 |
| Opus 5 | $0.00050 | $0.00888 |
| Sonnet 5 | $0.00020 | $0.00355 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
bb-customer 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BP Customer — Khách Hàng & Dịch Vụ
Phạm vi
Tầng 3: Động Cơ — Giữ chân, phát triển, và nhân bản khách hàng. Tạo 12 tài liệu chia 4 nhóm:
| Nhóm | Tên | Mô tả |
|---|---|---|
| 07.1 | Trải nghiệm KH | CX standards, onboarding, chăm sóc sau bán, NPS/CSAT |
| 07.2 | Xử lý khiếu nại | Quy trình khiếu nại, hoàn tiền/bảo hành, log tracker |
| 07.3 | Quản lý quan hệ KH | Phân loại KH, loyalty & retention, health score |
| 07.4 | Cộng đồng & Referral | Referral program, thu thập review |
Prompt files trong references/
| File | Loại | Mô tả |
|---|---|---|
man-customer-experience-standards.md |
MAN | Tiêu chuẩn trải nghiệm khách hàng |
sop-onboard-khach-hang.md |
SOP | SOP onboarding khách hàng |
sop-cham-soc-sau-ban.md |
SOP | SOP chăm sóc sau bán hàng |
frm-khao-sat-nps-csat.md |
FRM | Khảo sát NPS/CSAT |
sop-xu-ly-khieu-nai.md |
SOP | SOP xử lý khiếu nại |
pol-hoan-tien-bao-hanh.md |
POL | Chính sách hoàn tiền & bảo hành |
frm-log-khieu-nai.md |
FRM | Log theo dõi khiếu nại |
sop-phan-loai-kh.md |
SOP | SOP phân loại khách hàng |
man-loyalty-retention.md |
MAN | Chương trình loyalty & retention |
frm-customer-health-score.md |
FRM | Customer Health Score |
man-referral-program.md |
MAN | Chương trình referral |
sop-thu-thap-review.md |
SOP | SOP thu thập review/testimonial |
Quy trình sử dụng
Bước 1: Xác định tài liệu cần tạo
- Hỏi user cần tạo tài liệu nào (hoặc tạo toàn bộ nếu đang chạy từ Orchestrator)
- Recommend tài liệu ưu tiên theo loại hình DN nếu user chưa biết cần gì
Bước 2: Đọc prompt file tương ứng
- Đọc
${CLAUDE_PLUGIN_ROOT}/skills/bb-customer/references/<tên-file>.md - Prompt file chứa quy trình: thu thập thông tin → đề xuất template → xác nhận → sinh tài liệu → review
Bước 3: Thu thập thông tin
- Theo hướng dẫn trong prompt file, hỏi user các thông tin cần thiết
- Ghi nhận đầy đủ context trước khi sang bước tiếp
Bước 4: Xác nhận cấu trúc & nội dung (BẮT BUỘC)
- Trình bày dàn ý / cấu trúc tài liệu cho user xem trước
- Liệt kê các section chính, nội dung tóm tắt mỗi section
- CHỈ tạo file sau khi user confirm cấu trúc
- Nếu user yêu cầu chỉnh sửa cấu trúc → điều chỉnh → confirm lại
What ships with it
12 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.
- references/frm-customer-health-score.md 2.5 KB
- references/frm-khao-sat-nps-csat.md 2.4 KB
- references/frm-log-khieu-nai.md 2.3 KB
- references/man-customer-experience-standards.md 2.7 KB
- references/man-loyalty-retention.md 2.6 KB
- references/man-referral-program.md 2.7 KB
- references/pol-hoan-tien-bao-hanh.md 2.6 KB
- references/sop-cham-soc-sau-ban.md 2.3 KB
- references/sop-onboard-khach-hang.md 2.4 KB
- references/sop-phan-loai-kh.md 2.3 KB
- references/sop-thu-thap-review.md 2.8 KB
- references/sop-xu-ly-khieu-nai.md 2.8 KB
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 · 134 lines · 100 tokens per session scan A ff364815a54e
bb-customer is a skill published in the GitHub repository modoro-digital/VietNam-Business-Builder (55 stars, last pushed 4mo ago), licensed MIT. It adds 100 tokens to every session and 1,776 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…