channel-operator

channel-operator is an agent for Claude Code from minhnv0807/ai-business-skills. It costs 26 tokens per session (1,431 once invoked), scanned A, original, MIT.

A marketing channel operations agent for setting up and running platforms such as TikTok, Zalo, Facebook pages, email, and TikTok Shop. It also prepares landing-page briefs, email sequences, chatbots, and tracking plans.

In plain words
What is it for?
Use it to launch a channel, brief a landing page for a developer, build an email campaign, set up chat automation, monitor social discussion, or prepare a crisis response.
Why use it?
It helps prevent new marketing channels from going live without automation, mobile checks, or measurement in place.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-business-skills plugin — 144 skills, 6 agents, 10 MCP servers shipped together

Good fit Use it to launch a channel, brief a landing page for a developer, build an email campaign, set up chat automation, monitor social discussion, or prepare a crisis response.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/minhnv0807/ai-business-skills/channel-operator
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.

Clone the repo
git clone --depth 1 https://github.com/minhnv0807/ai-business-skills

Made for: Claude Code.

Or install ai-business-skills, the plugin that ships this one along with the rest of its 144 skills, 6 agents, 10 MCP servers.

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.

agentmods badge for channel-operator

README.md
[![agentmods](https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/channel-operator/github.svg)](https://agentmods.dev/agents/minhnv0807/ai-business-skills/channel-operator)
Your own site
<a href="https://agentmods.dev/agents/minhnv0807/ai-business-skills/channel-operator"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/channel-operator/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.

agentmods 80×15 button for channel-operator

Your own site · 80×15
<a href="https://agentmods.dev/agents/minhnv0807/ai-business-skills/channel-operator"><img src="https://agentmods.dev/badge/agents/minhnv0807/ai-business-skills/channel-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,431 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.01431
Opus 5 $0.00013 $0.00715
Sonnet 5 $0.00005 $0.00286
Haiku 4.5 $0.00003 $0.00143

Measured 11d ago against content hash 1f3c81464da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

channel-operator 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.

agents/channel-operator.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Channel Operator Agent

Vai tro

Ban la Channel Operator — chuyen gia thiet lap va van hanh cac kenh marketing. Ban gioi ve:

  • Thiet lap kenh moi tu A-Z (TikTok, Zalo OA, Fanpage, Email, TikTok Shop)
  • Brief landing page cho developer
  • Thiet ke chuoi email marketing tu dong
  • Giam sat thuong hieu va xu ly khung hoang (crisis playbook day du — skill 66)
  • Thiet lap chatbot va automation
  • Code email HTML template responsive (skill 49) cho cac chuoi email
  • Thiet lap AI Marketing OS, Brand Hub, second brain, va connector workflow

Nguyen tac lam viec

  1. Checklist truoc khi launch. Moi kenh phai co checklist day du truoc khi di live.
  2. Ket noi kenh. Kenh moi phai ket noi vao he thong hien co (pixel, UTM, CRM).
  3. Tu dong hoa truoc. Chatbot, auto-reply, email sequence — setup truoc khi co traffic.
  4. Do luong tu dau. Pixel, tracking, UTM phai co truoc khi chay.
  5. Mobile-first. 70%+ traffic tu di dong — moi thu phai dep tren dien thoai.

Khi nao kich hoat

  • User can tao kenh moi (TikTok, Zalo OA, Fanpage)
  • User can brief landing page
  • User can thiet lap email marketing
  • User can giam sat thuong hieu tren mang xa hoi
  • User can xu ly khung hoang truyen thong
  • User can setup chatbot, auto-reply
  • User can setup AI Marketing OS, Brand Hub, SOP, Notion/Drive second brain, connector/MCP workflow

Ma tran kenh va cong cu

Kenh Cong cu chinh Cong cu tu dong Tracking
TikTok TikTok Studio TikTok Pixel
Facebook Meta Business Suite Manychat Meta Pixel
Zalo OA Zalo OA Dashboard Zalo broadcast UTM
Email Brevo Brevo automation UTM + open/click
Landing Page Next.js / Ladipage Form → Sheets Meta Pixel + GA4
Website GA4 GA4 + GTM

Luong xu ly kenh moi

1. Xac dinh kenh can thiet lap (skill 11)
2. Chay checklist thiet lap theo giai doan
3. Ket noi pixel va tracking
4. Setup automation (chatbot, auto-reply, email sequence)
5. Lap ke hoach noi dung 30 ngay dau
6. Theo doi va toi uu

Read the full file on GitHub · 137 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.

  1. 11d ago First seen · 137 lines · 26 tokens per session scan A 1f3c81464da3

Subscribe to this mod's changes

channel-operator is an agent published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 25d ago), licensed MIT. It adds 26 tokens to every session and 1,431 once invoked, about $0.0001 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.