Use it when working on article-generation workflows, content-specific agents, publishing scripts, or integrations for sources such as arXiv and web pages.

It explains the project's structure and shared automation pattern so changes fit the right content area. It also documents the different topics and the tools each workflow uses.

How floodsung/gongzhonghao_agent_team configures Claude Code

Q: What is gongzhonghao_agent_team CLAUDE.md?

Repository instructions for a system that uses AI agents and scripts to create and publish articles to WeChat Official Accounts. Each content area has its own automation scripts, agents, and connected tools.

Reuse

Borrowing it

Nothing to install: this file belongs to floodsung/gongzhonghao_agent_team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/floodsung/gongzhonghao_agent_team/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/floodsung/gongzhonghao_agent_team

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/floodsung/gongzhonghao_agent_team/claude-md/github.svg)](https://agentmods.dev/instructions/floodsung/gongzhonghao_agent_team/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/floodsung/gongzhonghao_agent_team/claude-md"><img src="https://agentmods.dev/badge/instructions/floodsung/gongzhonghao_agent_team/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/floodsung/gongzhonghao_agent_team/claude-md"><img src="https://agentmods.dev/badge/instructions/floodsung/gongzhonghao_agent_team/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,044 This file is loaded in full into every session.

When invoked 1,044 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01044	$0.01044
Opus 5.5	$0.00418	$0.00418
Sonnet 5.5	$0.00209	$0.00209
Haiku 4.5	$0.00104	$0.00104

Measured 2mo ago against content hash 64a5ed6680fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gongzhonghao_agent_team CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Download images using curl

CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Media Agents automation system that uses Claude Code to automatically generate and publish articles to WeChat Official Accounts (公众号). Each subdirectory represents a different content vertical/topic area with its own automation scripts and Claude agents.

Architecture

Core Pattern

Each vertical follows the same architecture:

Python automation script (daily_*.py) - Orchestrates the workflow
Claude agents (.claude/agents/*.md) - Define specialized AI behaviors for content generation
MCP servers (.mcp.json) - Connect to external tools (WeChat publishing, Playwright for web scraping, arXiv for papers)

Verticals

Directory	Topic	Key Script
`media_agent/`	AI/Tech News	`daily_ai_news.py`
`digital_nomad/`	Digital Nomad/Solopreneur	`daily_nomad_news.py`
`investment_insights/`	Investment/Finance	`daily_investment_news.py`
`fuson/`	Fashion (Knitwear)	`daily_fashion.py`
`intelligent_unit/`	arXiv Paper Analysis	`daily_arxiv_papers.py`
`aml_compliance/`	AML/Sanctions Compliance	`daily_aml_news.py`
`military_frontier/`	Military/Defense	`daily_military_frontier.py`
`digital_tech/`	Digital Products/Reviews	`daily_digital_tech_news.py`

How It Works

Python script generates a dynamic prompt with current Beijing time and topic-specific search parameters
Script invokes Claude Code in headless mode (claude -p <prompt> --permission-mode bypassPermissions)
Claude uses MCP tools to:
- Search news via Playwright (Google News with time filters)
- Fetch detailed content from authoritative sources
- Download images using curl
- Write articles in Markdown format
- Publish to WeChat via wenyan-mcp server
Articles are saved to <vertical>/articles/ with naming pattern YYYYMMDD_HHMM_topic_keywords.md

Read the full file on GitHub · 116 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.

2mo ago First seen · 116 lines · 1,044 tokens per session scan A 64a5ed6680fb

Subscribe to this mod's changes

gongzhonghao_agent_team CLAUDE.md is an instructions file published in the GitHub repository floodsung/gongzhonghao_agent_team (61 stars, last pushed 9mo ago), licensed MIT. It adds 1,044 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Building agents Writing and docs

gongzhonghao_agent_team CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gongzhonghao_agent_team CLAUDE.mdfloodsung/gongzhonghao_agent_team	Instructions file	61	9mo ago	MIT	A	1,044	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gongzhonghao_agent_team: Instructions file for Claude Code