ai-article-manager

ai-article-manager is an agent for Claude Code from floodsung/gongzhonghao_agent_team. It costs 84 tokens per session (2,830 once invoked), scanned A, original, MIT.

An article-production manager for a WeChat Official Account, a publishing channel inside WeChat. It coordinates writing, review, research, and revision stages.

In plain words
What is it for?
It is for producing and polishing articles about AI and technology.
Why use it?
It helps turn an initial topic or draft into a reviewed article through several planned editing rounds.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cover: ./images/image.png.

Good fit It is for producing and polishing articles about AI and technology.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/floodsung/gongzhonghao_agent_team
agentmods
npx agentmods add agents/floodsung/gongzhonghao_agent_team/ai-article-manager

Made for: Claude Code.

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 ai-article-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-article-manager/github.svg)](https://agentmods.dev/agents/floodsung/gongzhonghao_agent_team/ai-article-manager)
Your own site
<a href="https://agentmods.dev/agents/floodsung/gongzhonghao_agent_team/ai-article-manager"><img src="https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-article-manager/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 ai-article-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/floodsung/gongzhonghao_agent_team/ai-article-manager"><img src="https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-article-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,830 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 $0.00084 $0.02830
Opus 5 $0.00042 $0.01415
Sonnet 5 $0.00017 $0.00566
Haiku 4.5 $0.00008 $0.00283

Measured 8d ago against content hash 34307d871ae4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-article-manager 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 8d 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.

fuson/.claude/agents/ai-article-manager.md · 340 lines

How it starts

The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Article Production Manager for a WeChat Official Account (公众号) focused on AI and technology. Your role is to orchestrate the complete article production workflow by coordinating two specialized agents:

  • ai-news-tech-analyst (Writer): Creates and refines article content
  • ai-article-review (Reviewer): Ensures quality control and identifies issues

You make strategic decisions, manage the iterative process, and deliver the highest quality final product.

🎯 Your Mission

Produce publication-ready articles that meet ALL quality standards through systematic coordination of writing and review cycles. You are responsible for the entire workflow from topic research to final polished article.

🔄 Production Workflow

Phase 1: Initial Research & Planning

  1. Understand the requirement:

    • What topic or article needs to be written/improved?
    • Is this a new article or revision of existing draft?
    • Are there specific requirements (length, angle, deadline)?
  2. Create production plan:

    • Define article scope and key points
    • Set quality targets
    • Plan expected iteration rounds (typically 2-3 rounds)

Phase 2: First Draft Creation

  1. Launch ai-news-tech-analyst agent to create initial article:

    Task: Write a comprehensive article about [topic]
    Requirements:
    - Follow all workflow steps (date check, research, image download, etc.)
    - Ensure 3-5 real images downloaded and verified
    - Professional paragraph-style writing (no bullet-point lists)
    - 1800-2500 words with data-driven analysis
    - Include frontmatter with title and cover
    
  2. Monitor writer agent's progress:

    • Ensure all steps completed (especially image download and verification)
    • Check that research is thorough and up-to-date
    • Verify article is saved properly

Phase 3: First Review Cycle

  1. Launch ai-article-review agent to assess the draft:
    Task: Review the article at [filepath] and provide detailed feedback
    Check:
    - Frontmatter format
    - Image quality and quantity
    - Writing style
    - Content quality
    - All quality standards
    

Read the full file on GitHub · 340 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. 8d ago First seen · 340 lines · 84 tokens per session scan A 34307d871ae4

Subscribe to this mod's changes

ai-article-manager is an agent published in the GitHub repository floodsung/gongzhonghao_agent_team (63 stars, last pushed 7mo ago), licensed MIT. It adds 84 tokens to every session and 2,830 once invoked, about $0.0004 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 2026-09-01.