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.
npx skills add djblack1209-coder/OpenClaw-Bot --skill social-autopilotgit clone --depth 1 https://github.com/djblack1209-coder/OpenClaw-BotWrote 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/skills/djblack1209-coder/openclaw-bot/social-autopilot)<a href="https://agentmods.dev/skills/djblack1209-coder/openclaw-bot/social-autopilot"><img src="https://agentmods.dev/badge/skills/djblack1209-coder/openclaw-bot/social-autopilot/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/skills/djblack1209-coder/openclaw-bot/social-autopilot"><img src="https://agentmods.dev/badge/skills/djblack1209-coder/openclaw-bot/social-autopilot.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 | $0.00077 | $0.01276 |
| Opus 5 | $0.00039 | $0.00638 |
| Sonnet 5 | $0.00015 | $0.00255 |
| Haiku 4.5 | $0.00008 | $0.00128 |
Grade A, and why
social-autopilot 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 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.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Social Autopilot — AI 自主社媒运营
定位
这不是等 严总 下命令的被动模式，而是完全自主的 AI 运营员。 每天按照预设日程表自动完成全部运营动作，只在需要决策时通知 严总。
每日自动运营日程
☀️ 早间 09:00 — 热点扫描与选题
- 执行
node tools/social-hotspot-monitor.mjs --platform all --min-score 6 - 扫描结果 + 选题库(
tools/social-topic-library.md) → 选出今天发布的 2-3 个选题 - 用
node tools/social-topic-scorer.mjs评分，≥7 分的进入内容生产 - 结果写入
memory/social/SOC-001-publish-runs.md - 向 严总 发送一条简报：「今日选题：[标题1] [标题2]，预计晚8点发」
🌙 午间 12:00-13:00 — 互动与蹭评
- 检查已发布内容的评论区，用
tools/social-comment-engine.mjs reply自动回复 - 用
tools/social-comment-engine.mjs scout扫描 3-5 个目标帖 - 用
tools/social-comment-engine.mjs generate-scout-comment生成蹭评内容 - 通过 Playwright 发布蹭评（需确保浏览器预热）
🌆 晚间 19:00 — 内容生产
- 读取人设
tools/social-persona.md - 基于早间选题，按人设风格生成完整内容
- 小红书内容：标题+正文+标签+封面描述
- X 内容：280字以内观点+引用/对比
- 执行预检
node tools/social-publish-preflight.mjs：- AI 身份暴露检测 → 不通过则重写
- 客服腔/营销号腔检测
- 标题吸引力评估
- 通过预检的内容保存为草稿
🌃 晚间 20:00-21:00 — 自动发布
- 确认浏览器登录状态（X + 小红书）
- 执行
node tools/social-workflow.mjs publish - 通过 Playwright 完成实际发布
- 记录发布状态到
memory/social/SOC-001-publish-runs.md - 发布成功后向 严总 推送通知（含链接）
🌙 晚间 21:00-22:00 — 发布后互动
- 新帖发布后 1 小时内，密集监控评论区
- 自动回复所有评论（保持人设风格）
- 主动蹭 2-3 个相关热帖的评论区
🌑 睡前 22:00 — 数据复盘
- 统计今日发布数据：阅读量、点赞、评论、新增粉丝
- 对比 KPI 目标（小红书单条阅读>500/X单条>200）
- 写入
memory/social/SOC-003-interactions.md - 如有未达标内容，分析原因并调整明日选题方向
自动化实现方式
方式一：OpenClaw Cron（推荐）
在 OpenClaw 中创建以下 cron 任务：
| 任务名 | 时间 | 动作 |
|---|---|---|
| 社媒早扫 | 每天 09:00 | 热点扫描 + 选题 + 简报 |
| 社媒午动 | 每天 12:30 | 评论互动 + 蹭评 |
| 社媒晚产 | 每天 19:00 | 内容生产 + 预检 |
| 社媒晚发 | 每天 20:30 | 自动发布（双平台） |
| 社媒复盘 | 每天 22:00 | 数据统计 + 复盘 |
方式二：HEARTBEAT.md 集成
在 HEARTBEAT.md 中添加社媒运营检查项，让每次心跳自动检查运营进度。
关键文件
| 文件 | 用途 |
|---|---|
tools/social-persona.md |
人设基准 |
tools/social-topic-library.md |
选题库 |
tools/social-interaction-strategy.md |
互动策略 |
tools/social-workflow.mjs |
工作流编排入口 |
tools/social-hotspot-monitor.mjs |
热点扫描 |
tools/social-comment-engine.mjs |
评论引擎 |
tools/social-publish-preflight.mjs |
发布预检 |
tools/social-browser-adapter.mjs |
浏览器发布适配 |
scripts/social_browser_worker.py |
Playwright 执行器 |
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 · 108 lines · 77 tokens per session scan A 59344f50d897
social-autopilot is a skill published in the GitHub repository djblack1209-coder/OpenClaw-Bot (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,276 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.