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/AGENTS.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/instructions/alansong2077/amplipost/agents-md)<a href="https://agentmods.dev/instructions/alansong2077/amplipost/agents-md"><img src="https://agentmods.dev/badge/instructions/alansong2077/amplipost/agents-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.
<a href="https://agentmods.dev/instructions/alansong2077/amplipost/agents-md"><img src="https://agentmods.dev/badge/instructions/alansong2077/amplipost/agents-md.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 | $0.02458 | $0.02458 |
| Opus 5 | $0.01229 | $0.01229 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
Amplipost AGENTS.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 9d 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.
**调用方式：** content-coordinator 通过 `curl` 发送 HTTP POST 到 `http://localhost:18060/mcp` How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amplipost — Agent 架构说明
本文件描述 Amplipost 的 Agent 设计，供 Claude Code 及其他 AI 工具读取。
系统定位
Amplipost 是一个全自动多平台内容营销中台。
- 用户输入：一句话指令（「帮我发小红书，主题是 AI 工具推荐」）
- 系统输出：内容已发布到目标平台，返回发布状态
不需要用户在中途确认内容、选择选项、提供图片。 所有决策由 Agent 自主完成。
Agent 结构
content-coordinator ← 主 Agent，全程调度
│
├── Phase 0: 读取 memory.md ← 历史经验、用户偏好、内容指纹
├── Phase 1-2: 解析输入 + 查找脚本
├── Phase 3: 生成各平台内容 ← 主 Agent 负责生成
│
├── Phase 3.5: ──► content-reviewer ← subagent：独立质量评审
│ 返回评审报告 JSON
│ pass=false 则按建议重写，最多2次
│
├── Phase 4: 配图处理
│
├── Phase 4.5: ──► publish-guard ← subagent：风控拦截
│ 返回 allow/delay/block
│ delay 则等待后发布，block 则跳过
│
├── Phase 5: 发布执行 ← 调用 4 个平台 Skill 脚本
├── Phase 6-7: 验证结果 + 输出报告
└── Phase 8: 更新 memory.md ← 发布记录 + 内容指纹
三 Agent 职责边界
| Agent | 职责 | 不做什么 |
|---|---|---|
| content-coordinator | 解析输入、生成内容、调度流程、报告结果 | 不自评内容质量、不做风控判断 |
| content-reviewer | 独立评审内容质量，给出评分和具体修改建议 | 不生成内容、不做发布决策 |
| publish-guard | 评估发布行为的风控风险，决定放行/延迟/拦截 | 不评价内容质量、不修改内容 |
| xiaohongshu-mcp | 小红书发布的底层执行层（Go+go-rod+CDP），监听 localhost:18060 | 不生成内容、不做任何判断 |
| Skill 脚本 | 闲鱼/B站/抖音的浏览器自动化发布 | 不生成内容、不做任何判断 |
分离 reviewer 的原因： 生成方对自己的内容天然存在主观偏差，容易打高分。独立 reviewer 用统一评分标准，能识别 AI 感词汇、内容同质化等问题。
分离 guard 的原因： 风控是行为维度的判断（频率、间隔、多样性），与内容质量无关，需要独立的历史数据视角。
智能化能力
内容生成（Agent 核心能力，不在 Skill 内执行）
Agent 根据用户输入，自主为每个目标平台生成独立内容：
| 平台 | 字数 | 风格 | 结构 |
|---|---|---|---|
| 小红书 | 200-300 字 | 第一人称，口语化，有情绪，真人感 | 痛点共鸣 → 干货 → 收尾 → 互动引导 |
| B站 | 800-1500 字 | 专业，数据支撑，深度 | 引言 → 核心分析 → 干货 → 误区 → 互动 |
| 抖音 | 150-500 字 | 短句，口语，强钩子 | 强钩子 → 核心干货 2-4 点 → 互动引导 |
| 闲鱼 | 标题 10-30 字 | 简洁，突出卖点 | 【新旧】商品名 规格 |
内容质量自评（生成后自动执行，不满足则重写）：
- 第一句话能让目标用户停下来吗？（钩子强度）
- 读完有实质收获，还是在凑字数？（信息密度）
- 像真人说话，还是 AI 模板？（真实感）
所有平台禁止：综上所述、首先其次、不禁感叹 等 AI 感词汇
平台智能推断
未指定平台时，Agent 根据内容类型自动推断：
| 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 |
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.
- 9d ago First seen · 216 lines · 2,458 tokens per session scan A d60d85fe7769
Amplipost AGENTS.md is an instructions file published in the GitHub repository AlanSong2077/Amplipost (45 stars, last pushed 4mo ago), licensed MIT. It adds 2,458 tokens to every session, about $0.0123 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.