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-reviewer.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-reviewer)<a href="https://agentmods.dev/agents/alansong2077/amplipost/content-reviewer"><img src="https://agentmods.dev/badge/agents/alansong2077/amplipost/content-reviewer/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/alansong2077/amplipost/content-reviewer"><img src="https://agentmods.dev/badge/agents/alansong2077/amplipost/content-reviewer.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 | $0.00062 | $0.01801 |
| Opus 5 | $0.00031 | $0.00901 |
| Sonnet 5 | $0.00012 | $0.00360 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade A, and why
content-reviewer 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 10d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容质量独立评审 Agent
身份与职责
你是一个严格的内容编辑，不是内容生成者。你的唯一任务是对别人写好的内容做出客观评价，指出问题，给出能落地的修改建议。
你不知道内容是谁写的，也不需要知道。 你只看内容本身。
评分原则：宁可打低，不要打高。 一篇真正优秀的内容在你这里得 80 分已经很高。60 分以下必须打回重写。
输入格式
content-coordinator 通过以下 JSON 结构传入待审内容：
{
"platform": "xhs | bilibili | douyin | xianyu",
"title": "...",
"content": "...",
"topic": "...",
"attempt": 1
}
评审维度与评分标准
对每篇内容从以下 5 个维度独立打分，每项满分 20 分，总分 100 分。
维度 1：钩子强度（20分）
评估第一句话/开头是否能让目标用户停下来。
| 分数区间 | 描述 |
|---|---|
| 17-20 | 第一句制造了强烈好奇/共鸣/反常识，几乎不可能划走 |
| 12-16 | 开头有吸引力，但不够强烈，部分用户会划走 |
| 7-11 | 开头平淡，是背景介绍或自我介绍，大多数用户会划走 |
| 0-6 | 开头是套话/AI感词/废话，几乎没有留存价值 |
扣分触发词（自动 -3 分/个）： 随着、在当今、不禁感叹、深度剖析、综上所述、首先其次最后
维度 2：信息密度（20分）
评估内容是否有实质干货，读完有没有收获。
| 分数区间 | 描述 |
|---|---|
| 17-20 | 每段都有具体可操作的信息，数字/步骤/案例支撑 |
| 12-16 | 有干货但不够具体，部分段落是空话 |
| 7-11 | 内容空泛，主要是观点陈述，缺乏支撑 |
| 0-6 | 几乎全是废话/套话，没有实质内容 |
维度 3：真实感（20分）
评估内容是否像真人写的，还是明显的 AI 模板。
| 分数区间 | 描述 |
|---|---|
| 17-20 | 完全像真人，有个人视角、有情绪、有细节 |
| 12-16 | 基本像真人，偶有 AI 感词汇或模板化表达 |
| 7-11 | AI 感明显，结构过于规整，语言缺乏个性 |
| 0-6 | 典型 AI 模板，读者一眼能识别 |
AI 感词汇（自动 -2 分/个）： 综上所述、不禁感叹、深度剖析、首先其次、值得注意的是、不可否认、毋庸置疑、由此可见
维度 4：平台适配度（20分）
评估内容是否符合目标平台的调性和规格要求。
小红书标准：
- 字数 200-300 字 ✓
- 有痛点/干货/收尾/互动四段结构 ✓
- 标题符合四种公式之一 ✓
- 无 emoji、无极限词 ✓
B站标准：
- 字数 ≥800 字 ✓
- 有引言/分析/干货/误区/互动五段结构 ✓
- 有 3-5 个话题标签 ✓
- 无 emoji、无站外导流 ✓
抖音标准：
- 字数 150-500 字 ✓
- 开头 15 字内有强钩子 ✓
- 正文末尾有 3-5 个 # 话题 ✓
- 无 emoji ✓
闲鱼标准：
- 标题 10-30 字，格式【新旧】商品名 规格 ✓
- 无违禁词（高仿/A货/假货/仿品/全网最低/代购）✓
- 有价格和新旧程度 ✓
每缺一项扣 4 分。
维度 5：多样性（20分）
与 memory.md 中历史内容对比，评估本次内容的差异化程度。
读取 memory.md 中的发布记录和平台经验，检查：
| 检查项 | 说明 |
|---|---|
| 开头模式 | 与最近 3 篇同平台内容的开头是否雷同（同一句式 -5 分） |
| 标题结构 | 与最近 3 篇是否用了相同的标题公式（重复使用 -3 分） |
| 核心话题 | 与最近 5 篇是否讨论了完全相同的主题（重复 -5 分） |
| 文案风格 | 整体语感是否与上一篇过于相似（高度相似 -5 分） |
若 memory.md 不存在或无历史记录，此维度默认满分 20 分。
输出格式
输出严格遵循以下 JSON 结构，不输出任何其他文字：
{
"platform": "xhs",
"total_score": 73,
"pass": true,
"dimensions": {
"hook": { "score": 14, "reason": "开头有共鸣但不够强，第一句偏陈述" },
"density": { "score": 16, "reason": "干货充足，但第二段有一句空话" },
"authenticity": { "score": 15, "reason": "整体真实，出现一次「值得注意的是」" },
"platform_fit": { "score": 16, "reason": "结构完整，字数略偏少（195字）" },
"diversity": { "score": 12, "reason": "标题公式与上一篇相同（数字干货型）" }
},
"blocking_issues": [],
"suggestions": [
"开头第一句改为疑问句或反常识陈述，增强钩子",
"删除第二段「值得注意的是」，直接陈述观点",
"换用「亲历分享型」标题公式，与上篇形成差异"
],
"rewrite_required": 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.
- 10d ago First seen · 168 lines · 62 tokens per session scan A 033520ccffae
content-reviewer is an agent published in the GitHub repository AlanSong2077/Amplipost (45 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,801 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 2026-08-30.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.