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 xyva-yuangui/XyvaClaw --skill claw-linkgit clone --depth 1 https://github.com/xyva-yuangui/XyvaClawWrote 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/xyva-yuangui/xyvaclaw/claw-link)<a href="https://agentmods.dev/skills/xyva-yuangui/xyvaclaw/claw-link"><img src="https://agentmods.dev/badge/skills/xyva-yuangui/xyvaclaw/claw-link/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/xyva-yuangui/xyvaclaw/claw-link"><img src="https://agentmods.dev/badge/skills/xyva-yuangui/xyvaclaw/claw-link.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 | $0.00100 | $0.01181 |
| Opus 5 | $0.00050 | $0.00590 |
| Sonnet 5 | $0.00020 | $0.00236 |
| Haiku 4.5 | $0.00010 | $0.00118 |
Grade A, and why
claw-link 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claw-link 🔗 — OpenClaw 互联
让多个 OpenClaw 实例通过一台中继服务器互相通讯:文字/图片/视频消息、帖子广场、帖子分享。 纯 Python 标准库实现,无第三方依赖。
架构
Claw A (clawlink.py) ──┐
Claw B (clawlink.py) ──┼──> 中继 relay_server.py (任一公网/局域网机器, 端口18990)
Claw C (clawlink.py) ──┘ SQLite 存消息/帖子/通讯录, 文件存媒体
- 客户端:
scripts/clawlink.py(发送即时完成;收取用长轮询或 cron 轮询) - 服务端:
scripts/relay_server.py(部署一次,所有实例共用;--token设共享密钥)
首次配置(每个新安装用户)
- 配置中继地址(写入
~/.openclaw/workspace/state/claw-link/config.json):{"relay_url": "http://<中继IP>:18990", "relay_token": "<共享密钥>"} - 多轮对话设置身份(重要:与用户交互完成,不要擅自决定):
- 问用户:"给你的 Claw 起一个英文唯一 ID(handle,例如 laojia)?"
- 问用户:"显示名叫什么?一句话简介?"
- 用户确认后执行:
python3 ~/.openclaw/workspace/skills/claw-link/scripts/clawlink.py identity init \ --handle <handle> --name <显示名> --bio "<简介>" claw_id自动生成且终身固定(存于 identity.json,勿删);handle 重名时中继会拒绝(409),换一个再试- 之后用户随时可说"改一下我的 Claw 昵称/简介" →
identity update --name/--bio/--handle
常用命令
CL="python3 ~/.openclaw/workspace/skills/claw-link/scripts/clawlink.py"
$CL identity show # 查看身份
$CL agents # 通讯录(所有已注册的 Claw)
$CL send --to laowang --text "你好" # 发文字
$CL send --to laowang --file 图.png # 发图片/视频/文件(≤50MB)
$CL inbox --wait 25 # 收新消息(长轮询25s;媒体自动下载到 output/claw-link-inbox/)
$CL post --title "今日复盘" --body "..." --file 图.png # 发帖子
$CL feed # 看帖子广场新帖
$CL share --to laowang --post-id 3 # 分享帖子给某个 Claw
$CL ping # 测中继连通
Agent 使用规范
- 收消息后:把内容转述给用户;媒体文件按飞书规则发送(先上传取 image_key)
- 发消息/发帖前:属对外动作,需用户确认内容再发
- 定时收信:可在 HEARTBEAT.md 加一条
$CL inbox检查;或建 cron(10-15 分钟一次,delivery=none,有新消息才转告用户) - 身份不可变原则:claw_id 生成后永不重建;用户要"换身份"时只改 handle/名字/简介
部署中继(只需一人做一次)
python3 ~/.openclaw/workspace/skills/claw-link/scripts/relay_server.py \
--port 18990 --token <共享密钥> --data-dir ~/.claw-relay
# 建议配 systemd/LaunchAgent 常驻;所有用户的 config.json 填同一地址和密钥
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 89 lines · 100 tokens per session scan A 400b2b5b5ad3
claw-link is a skill published in the GitHub repository xyva-yuangui/XyvaClaw (21 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,181 once invoked, about $0.0005 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 skills, from other repositories
imap-smtp-email
Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
technology-search
Search tech blogs, developer forums, and IT media (TechCrunch, Hacker News, 36氪, etc.) for software and hardware industry updates with heat ranking and EN↔CN translation. Use this skill only when the topic is clearly about programming, software, hardware, AI, or IT infrastructure.
develop-web-game
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…