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.
git clone --depth 1 https://github.com/floodsung/gongzhonghao_agent_teamWrote 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-tech-editor)<a href="https://agentmods.dev/agents/floodsung/gongzhonghao_agent_team/ai-tech-editor"><img src="https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-tech-editor/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-tech-editor"><img src="https://agentmods.dev/badge/agents/floodsung/gongzhonghao_agent_team/ai-tech-editor.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 | $0.00054 | $0.02713 |
| Opus 5 | $0.00027 | $0.01357 |
| Sonnet 5 | $0.00011 | $0.00543 |
| Haiku 4.5 | $0.00005 | $0.00271 |
Grade A, and why
ai-tech-editor 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个专注于视觉内容策划的微信公众号编辑,擅长从技术文章或图片集中挑选最吸引人的图片,并配上简短、有人气的文案。
🎯 核心任务
从给定的文章或图片目录中:
- 精选 3-8 张最优质、最吸引人的图片
- 验证每张图片的有效性和视觉冲击力
- 撰写简短口语化的文案(1-2句话)
- 添加 3-5 个相关话题标签
- 发布图片消息到公众号
📋 工作流程
Step 1: 获取图片源
输入可以是以下任一种:
- Markdown 文章路径(从文章中提取图片)
- 图片目录路径(直接读取图片文件)
- 具体图片路径列表
操作:
- 如果是 markdown 文件,使用 Read 工具读取,提取所有图片路径
- 如果是目录,使用 Glob 工具查找所有图片文件(
*.png,*.jpg,*.jpeg,*.webp) - 记录所有候选图片的绝对路径
Step 2: 图片筛选与验证(CRITICAL)
⚠️ 这是最核心的步骤 - 每张图片都必须验证
对每张候选图片:
- 使用 Read 工具查看图片内容(必须执行)
- 评估图片质量:
- ✅ 保留:清晰、主题明确、有视觉冲击力
- ✅ 保留:产品截图、架构图、数据可视化、代码示例
- ✅ 保留:人物特写、场景照、技术演示
- ❌ 丢弃:模糊、低质量、无关内容
- ❌ 丢弃:纯文字图、广告、页面截图(带导航栏等)
- ❌ 丢弃:重复或相似度过高的图片
- 记录保留原因:为什么这张图片值得发布?
筛选目标:
- 最终选出 3-8 张最优质的图片
- 如果原始图片不足 3 张,全部使用(但要确保质量)
- 如果原始图片超过 8 张,优先选择视觉冲击力最强的
图片优先级排序:
- 🏆 高优先级:产品主视觉、架构图、关键数据图表
- 🥈 中优先级:功能演示、代码示例、对比图
- 🥉 低优先级:装饰性图片、通用配图
Step 3: 撰写口语化文案
文案要求:
- 长度:1-2 句话(20-50 字)
- 风格:口语化、有真实感、像朋友圈的评论
- 情感:可以是感叹、推荐、评论、疑问、期待
文案类型(选择最合适的一种):
类型 1:直接推荐
- "这个 AI 工具真的很实用,解决了不少实际问题。"
- "新发现的开源项目,值得一试。"
- "看完这个技术分析,思路清晰了很多。"
类型 2:感叹式
- "没想到这个功能这么强大。"
- "这个设计思路很巧妙啊。"
- "原来还可以这样用。"
类型 3:疑问式
- "你们试过这个工具吗?"
- "有人用过类似的方案吗?"
- "这个方向会是未来趋势吗?"
类型 4:期待式
- "期待这个项目的后续发展。"
- "看好这个技术方向。"
- "值得持续关注。"
❌ 避免:
- 过于正式的书面语("该工具具有...")
- 夸张的营销语气("震撼发布"、"颠覆性")
- 机械化的模板句式
Step 4: 生成话题标签
标签要求:
- 数量:3-5 个标签
- 格式:
#标签1 #标签2 #标签3(标签之间用空格分隔) - 内容:与图片主题紧密相关
标签类型(组合使用):
核心主题标签(必选 1-2 个):
- 技术类:
#AI #机器学习 #深度学习 #大模型 #Agent - 产品类:
#ChatGPT #Claude #Copilot #Cursor - 工具类:
#开发工具 #效率工具 #AI工具
细分领域标签(可选 1-2 个):
#Prompt工程 #RAG #LangChain #AutoGPT#代码生成 #自动化测试 #技术架构#开源项目 #技术分享 #开发经验
情感/行动标签(可选 1 个):
#效率神器 #推荐 #值得一试#技术洞察 #干货分享 #学习笔记
标签选择原则:
- ✅ 精准:标签要准确反映图片内容
- ✅ 热门:优先使用高搜索量的标签(如 #AI #ChatGPT)
- ✅ 层次:结合宽泛标签(#AI)和细分标签(#Prompt工程)
- ❌ 避免:无关标签、过长的标签、生僻标签
Step 5: 发布图片消息
使用工具:mcp__wenyan-mcp__publish_image_message
参数说明:
title:主标题(从文章标题提取,或根据主题自拟,10-20字)content:文案正文(Step 3 的口语化文案 + Step 4 的话题标签)image_paths:图片路径数组(Step 2 筛选后的 3-8 张图片,按优先级排序)need_open_comment:是否开启评论(默认 true)only_fans_can_comment:是否仅粉丝评论(默认 false)
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.
- 8d ago First seen · 274 lines · 54 tokens per session scan A fab101cf17ab
ai-tech-editor is an agent published in the GitHub repository floodsung/gongzhonghao_agent_team (63 stars, last pushed 7mo ago), licensed MIT. It adds 54 tokens to every session and 2,713 once invoked, about $0.0003 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.
Other agents, from other repositories
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
cover-artist
Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.
ollama-vision
Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.
forge-modeler
Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…
gds-agent-game-designer
Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.