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.
git clone --depth 1 https://github.com/floodsung/gongzhonghao_agent_teamnpx agentmods add agents/floodsung/gongzhonghao_agent_team/ai-article-managerWrote 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/agents/floodsung/gongzhonghao_agent_team/ai-article-manager)<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.
<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>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 | $0.00084 | $0.02830 |
| Opus 5.5 | $0.00034 | $0.01132 |
| Sonnet 5.5 | $0.00017 | $0.00566 |
| Haiku 4.5 | $0.00008 | $0.00283 |
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 2mo 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 — 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
-
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)?
-
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
-
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 -
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
- 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
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.
- 2mo ago First seen · 340 lines · 84 tokens per session scan A 34307d871ae4
ai-article-manager is an agent published in the GitHub repository floodsung/gongzhonghao_agent_team (61 stars, last pushed 9mo ago), licensed MIT. It adds 84 tokens to every session and 2,830 once invoked, about $0.0003 per session on Opus 5.5. 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.
ai-article-manager compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-article-managerfloodsung/gongzhonghao_agent_team | Agent | 61 | 9mo ago | MIT | A | 84 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |