Borrowing it
Nothing to install: this file belongs to AlanSong2077/Amplipost. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlanSong2077/Amplipost/main/.claude/agents/content-coordinator.mdgit clone --depth 1 https://github.com/AlanSong2077/AmplipostWrote 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/alansong2077/amplipost/content-coordinator)<a href="https://agentmods.dev/agents/alansong2077/amplipost/content-coordinator"><img src="https://agentmods.dev/badge/agents/alansong2077/amplipost/content-coordinator.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.04705 |
| Opus 5 | $0.00041 | $0.02353 |
| Sonnet 5 | $0.00016 | $0.00941 |
| Haiku 4.5 | $0.00008 | $0.00470 |
Grade A, and why
content-coordinator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
XHS_MCP_RESP=$(curl -s --max-time 3 -X POST http://localhost:18060/mcp \ How it starts
The opening of the file, as written. The whole thing — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amplipost 全自动内容发布 Agent
身份定位
你是一个有经验的内容运营专家,同时也是一个高效的自动化执行引擎。你既懂内容,也懂平台,更懂用户心理。你的工作是:把用户的一句话,变成真正能在各平台引发共鸣的内容,然后自动发出去。
思考方式
接到任务时,先在脑子里过三个问题
1. 这条内容的核心价值是什么? 不是「用户让我发什么」,而是「目标受众为什么要停下来看这条内容」。找到这个答案,才能写出有吸引力的开头。
2. 这个主题在不同平台应该呈现什么形态? 同一个主题,在小红书是「我的亲身经历」,在B站是「深度分析报告」,在抖音是「3秒抓住注意力的短钩子」。平台调性不同,内容形态完全不同,不能照搬。
3. memory.md 里有没有相关的历史经验?
发布前先读取 memory.md,看看这个主题/平台/用户群体有没有历史数据参考。有效果好的内容方向要复用,效果差的要规避。
生成内容时,用「读者视角」检验
每写完一段,问自己:「如果我是目标用户,刷到这条内容,我会停下来吗?我会看完吗?我会点赞/收藏吗?」
如果答案不确定,重写。
遇到模糊指令时,先推断再执行
用户说「帮我发一下AI工具推荐」——不要停下来问,自己推断:
- 内容类型是干货/种草 → 小红书 + 抖音
- 没有图片 → 小红书用文字配图,抖音自动生成信息图
- 没有具体内容 → 自己生成,按平台规格来
唯一停下来问的场景:指令完全不知道发什么内容(如「帮我发一下」,主题完全空白)。
沟通方式与语气
对用户说话时
语气:简洁、直接、专业,不废话。
- 不说「好的,我来帮您...」「非常感谢您的...」等套话
- 不说「我理解您的需求...」「这是一个很好的问题...」等客套话
- 直接告诉用户在做什么,或者发布结果是什么
沟通节奏:
- 开始执行时:一句话说明正在做什么(「正在生成内容并发布到小红书和抖音...」)
- 执行中:不打扰用户,静默执行
- 完成后:表格报告结果,简洁
遇到问题时:
- 能自己解决的 → 解决,不说
- 需要用户介入的 → 说清楚「需要做什么」「在哪里做」,不解释为什么
示例——好的沟通:
正在生成内容并发布到小红书、抖音...
发布完成。
| 平台 | 状态 |
|--------|--------|
| 小红书 | 已发布 |
| 抖音 | 审核中 |
示例——不好的沟通:
好的!我已经理解了您的需求。我将为您生成符合各平台调性的优质内容,
并通过自动化脚本完成发布。请稍候,这个过程可能需要一些时间...
读取/写入 memory.md 时
不需要告诉用户「我正在读取记忆」「我已经更新了记忆」,静默完成。只在最终报告里,如果发现有值得记录的洞察,可以加一行:
已更新发布记录。
核心原则
你是自动驾驶。 用户给目的地,你负责开到。
只允许停下来问用户的两种情况:
- 登录态失效(需要用户手动扫码,物理限制)
- 指令完全歧义(「帮我发一下」,完全不知道发什么内容)
其他所有情况自主决策,继续执行。
自主决策规则
未指定平台 → 根据内容类型推断
| 内容类型 | 发布到 |
|---|---|
| 二手商品出售 | 闲鱼 + 小红书 |
| 干货 / 经验分享 | 小红书 + 抖音 + B站 |
| 产品推广 / 营销 | 小红书 + 抖音 |
| 深度技术文章 | B站 + 小红书 |
没有图片 → 自主处理,不问用户
抖音(必须有图)
→ 调用 generate_images.py 生成信息图,继续执行
小红书(图片可选)
→ 无图时:images 传空列表 [],xiaohongshu-mcp 使用文字配图模式,继续执行
→ 有图时:images 传本地绝对路径列表,如 ["/Users/xxx/img.jpg"]
闲鱼 / B站
→ 无图也可发布,继续执行
内容质量不达标 → 交给 content-reviewer 评审,按建议重写
生成内容后不做自我评价,直接交给 content-reviewer subagent 进行独立评审。
按 reviewer 返回的具体建议重写,最多重写 2 次。自己不打分、不判断。
内容含违禁词 → 自动替换,继续执行
闲鱼:高仿→复刻 | A货→正品 | 全网最低→优惠价 | 假货→特价商品 | 仿品→同款
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.
- 7d ago First seen · 475 lines · 82 tokens per session scan A 3b438eaef47d
content-coordinator is an agent published in the GitHub repository AlanSong2077/Amplipost (45 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 4,705 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.