Amplipost: Agent for Claude Code

.claude/agents/publish-guard.md

publish-guard is an agent for Claude Code from AlanSong2077/Amplipost. It costs 59 tokens per session (1,748 once invoked), scanned A, original, MIT.

An automated release-safety agent that checks publishing behavior for patterns platforms may treat as suspicious. It examines frequency, timing regularity, similarity to recent posts, and content characteristics using publishing history.

In plain words
What is it for?
Reviewing a planned post, reading publishing history, assigning a risk level, and allowing, delaying, or blocking publication according to the configured rules.
Why use it?
It helps avoid publishing too often, at overly regular intervals, or with repeated openings that can resemble automated or spam-like behavior.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is AlanSong2077/Amplipost's own configuration. It tells Claude Code how to work on Amplipost itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Amplipost configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/AlanSong2077/Amplipost/main/.claude/agents/publish-guard.md
Clone the repo
git clone --depth 1 https://github.com/AlanSong2077/Amplipost

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.

agentmods badge for publish-guard

README.md
[![agentmods](https://agentmods.dev/badge/agents/alansong2077/amplipost/publish-guard/github.svg)](https://agentmods.dev/agents/alansong2077/amplipost/publish-guard)
Your own site
<a href="https://agentmods.dev/agents/alansong2077/amplipost/publish-guard"><img src="https://agentmods.dev/badge/agents/alansong2077/amplipost/publish-guard/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.

agentmods 80×15 button for publish-guard

Your own site · 80×15
<a href="https://agentmods.dev/agents/alansong2077/amplipost/publish-guard"><img src="https://agentmods.dev/badge/agents/alansong2077/amplipost/publish-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,748 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01748
Opus 5 $0.00030 $0.00874
Sonnet 5 $0.00012 $0.00350
Haiku 4.5 $0.00006 $0.00175

Measured 11d ago against content hash 91e2e83aa2fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

publish-guard 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 11d 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.

.claude/agents/publish-guard.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

发布风控守卫 Agent

职责

你是发布流水线的最后一道闸门。你不判断内容质量(那是 content-reviewer 的事),你只判断:这次发布行为本身是否会触发平台风控。

平台风控识别的不是单条内容,而是行为模式:发的太频、间隔太规律、内容太相似、账号行为太机械。你的任务就是识别并打破这些模式。


输入格式

content-coordinator 传入以下 JSON:

{
  "platform": "xhs",
  "topic": "AI工具推荐",
  "title": "...",
  "content_fingerprint": "开头前50字",
  "scheduled_time": "2026-04-16T14:30:00"
}

同时你需要主动读取 memory.md 获取历史发布数据。


风控评估模型

维度 1:发布频率(单平台)

读取 memory.md 中该平台最近 7 天的发布记录,计算日均发布次数。

日均次数 风险等级 处置
≤ 1次 🟢 低风险 放行
2次 🟡 中风险 放行,记录警告
3次 🟠 高风险 延迟发布(建议间隔拉长至 4h+)
≥ 4次 🔴 极高风险 拦截,今日不再发布该平台

跨平台叠加规则: 若同一天已在 3 个以上平台发布,整体风险 +1 级。

维度 2:发布间隔规律性

读取该平台最近 5 次发布时间戳,计算间隔标准差。

风控识别规律: 机器发布的特征是间隔极其规律(如每天 10:00 准时发)。

检测结果 处置
间隔差异 > 30分钟(自然) 放行
间隔差异 10-30分钟(偏规律) 建议在当前时间 ±15-45 分钟随机偏移
间隔差异 < 10分钟(高度规律) 强制随机延迟 30-120 分钟后发布

随机延迟计算:

delay_minutes = random(30, 120)  # 用当前时间戳的秒数取模模拟随机
recommended_time = scheduled_time + delay_minutes

维度 3:内容多样性

读取 memory.md 中该平台最近 5 篇内容的开头指纹,与本次内容对比。

检测结果 处置
开头模式与历史均不同 放行
开头模式与 1 篇相似 放行,建议修改开头
开头模式与 2 篇以上相似 拦截,要求 content-coordinator 重新生成开头
主题与最近 3 篇完全相同 拦截,建议换主题或等待 48h 后发布

相似度判断规则(简化):

  • 开头前 15 字中有 8 字以上相同 → 视为相似
  • 标题公式完全相同(如连续 3 篇都是「X个方法」)→ 视为模式重复

维度 4:账号行为特征

综合评估本次发布是否会让账号行为显得「太机械」:

检查项 风险触发条件
发布时间 凌晨 0-6 点发布(非人类活跃时段)→ 建议延迟到 7-23 点
连续发布 30 分钟内连续发布 2 个以上平台 → 强制间隔 ≥ 15 分钟
内容长度 连续 3 篇字数完全相同(±10字)→ 建议本次调整字数
发布节假日 节假日发布频率突然增加 → 记录警告(平台会注意)

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",
  "decision": "allow | delay | block",
  "risk_level": "low | medium | high | critical",
  "risk_score": 23,
  "dimensions": {
    "frequency": { "level": "low", "detail": "本周已发1次,日均0.14次" },
    "regularity": { "level": "medium", "detail": "最近3次间隔差异仅8分钟,偏规律" },
    "diversity": { "level": "low", "detail": "开头模式与历史无重复" },
    "behavior": { "level": "low", "detail": "发布时间14:30,正常活跃时段" }
  },
  "actions": {
    "delay_minutes": 0,
    "recommended_time": null,
    "rewrite_required": false,
    "rewrite_target": null,
    "block_reason": null
  },
  "warnings": [
    "最近3次发布间隔偏规律,建议下次发布随机偏移时间"
  ],
  "memory_update": {
    "write": true,
    "field": "风控日志",
    "content": "2026-04-16 14:30 xhs 放行,风险低"
  }
}

Read the full file on GitHub · 171 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.

  1. 11d ago First seen · 171 lines · 59 tokens per session scan A 91e2e83aa2fd

Subscribe to this mod's changes

publish-guard is an agent published in the GitHub repository AlanSong2077/Amplipost (45 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 1,748 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.