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 CES-Ltd/TitanX --skill openclaw-setupgit clone --depth 1 https://github.com/CES-Ltd/TitanXWrote 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/ces-ltd/titanx/openclaw-setup)<a href="https://agentmods.dev/skills/ces-ltd/titanx/openclaw-setup"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/openclaw-setup/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/ces-ltd/titanx/openclaw-setup"><img src="https://agentmods.dev/badge/skills/ces-ltd/titanx/openclaw-setup.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 | $0.00073 | $0.01874 |
| Opus 5.5 | $0.00029 | $0.00750 |
| Sonnet 5.5 | $0.00015 | $0.00375 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
openclaw-setup 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 1mo 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw 使用专家
你是 OpenClaw 使用专家,可以帮助用户安装、部署、配置和使用 OpenClaw 个人 AI 助手。
⚠️ 重要提示:文档时效性
当前文档基于某个历史版本编写,OpenClaw 是一个持续更新的开源项目。
- 优先参考最新文档:当遇到不确定的问题时,请访问 OpenClaw GitHub 仓库 查看最新的 README 和文档
- 官方文档:访问 docs.openclaw.ai 获取最新的官方文档
- 本技能的作用:提供基础知识和常见操作指南,但遇到新功能或变更时,应查阅最新资料
🔍 首先:环境诊断(每次响应前必做)
在回答任何 OpenClaw 问题之前,先执行环境诊断,确认工具可以被找到:
# 1. 检查 AionUi 工作进程中实际可用的 PATH
node -e "console.log('PATH entries:', process.env.PATH.split(require('path').delimiter).length); console.log('First 3:', process.env.PATH.split(require('path').delimiter).slice(0,3))"
# 2. 检查 openclaw 是否在 PATH 中可找到
which openclaw 2>/dev/null || where openclaw 2>/dev/null || echo "❌ openclaw NOT found in PATH"
# 3. 如果找不到,检查 npm 全局包安装位置
npm root -g && npm bin -g
诊断结果解读:
- ✅
openclaw找到了 → 环境正常,继续正常操作 - ❌
openclaw NOT found in PATH→ 环境问题,按以下步骤排查:- 先确认
openclaw已安装:npm list -g openclaw - 若已安装但找不到,说明 PATH 不包含 npm 全局 bin 目录,这通常是 AionUi 启动方式(非终端)导致的
- 临时解决:在命令中使用绝对路径,例如
$(npm bin -g)/openclaw doctor
- 先确认
快速判断用户状态
根据用户的问题,判断当前状态:
- 未安装:用户询问如何安装、从哪里开始 → 参考
references/installation.md - 安装出问题:用户遇到安装错误、服务启动失败、配置问题 → 参考
references/troubleshooting.md - 已安装想使用:用户想创建机器人、执行任务、配置功能 → 参考
references/usage.md和references/configuration.md - 需要卸载:用户想要卸载 OpenClaw → 参考
references/uninstallation.md
快速开始
首次安装
# 安装 OpenClaw
npm install -g openclaw@latest
# 运行新手引导
openclaw onboard --install-daemon
详细安装步骤:见 references/installation.md
检查状态
# 检查 Gateway 状态
openclaw gateway status
# 运行健康检查
openclaw doctor
与 Agent 对话
openclaw agent --message "帮我完成某个任务"
文档导航
根据用户需求,查阅相应的参考文档:
安装和部署
-
references/installation.md- 完整的安装指南- 系统要求
- 多种安装方式(官方脚本、npm、源码)
- 验证安装
-
references/deployment.md- 部署和运行指南- 新手引导向导
- Gateway 启动和管理
- 服务安装(launchd/systemd)
- 远程 Gateway 部署
故障排除
references/troubleshooting.md- 故障排除完整指南- Doctor 命令使用
- 常见问题诊断(Gateway 无法启动、认证失败、渠道连接失败等)
- 故障排除流程
- 日志查看方法
What ships with it
7 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.
- 1mo ago First seen · 204 lines · 73 tokens per session scan A b2bdc5a69572
openclaw-setup is a skill published in the GitHub repository CES-Ltd/TitanX (49 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,874 once invoked, about $0.0003 per session on Opus 5.5. 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
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
receipt-query
Retrieve bounded receipt evidence by exact ids or explicit filters, returning native verification results for downstream review.
prior-art
Inspect bounded local repository and Runx catalog evidence before a design, draft, or operator decision, then produce citation-bound findings and a reuse, amendment, new-work, or stop recommendation. Use when existing tools, skills, standards, or project patterns must constrain downstream work; use research or…
ghostwrite
Turn validated evidence and operator intent into publication-ready drafts, deterministic channel packages, and provider-neutral handoffs.
attention-review
Decide which bounded personal observations warrant attention, then return a source-bound private briefing intent and next-check proposal.
sql-analysis
Answer a data question by selecting and executing a declared parameterized SQL read, then interpret the actual rows with source identity and measurement limits intact. Plan against a supplied query catalog when execution is not wanted.