[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-82545":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":14,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":23,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":34,"lastSyncTime":35,"discoverSource":36},82545,"openclaw-runbook","digitalknk\u002Fopenclaw-runbook","digitalknk","Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.","https:\u002F\u002Fdigitalknk.github.io\u002Fopenclaw-runbook\u002F",null,"Astro",1100,99,19,1,0,4,7,12,"MIT License",false,"main",true,[25,26,27,28,29,30],"ai-agents","openclaw","runbook","security-hardening","self-hosting","tailscale","2026-06-12 02:04:26","# OpenClaw Runbook\n\n> Checked against OpenClaw at commit `5dccba7405` (`2026-05-25`)\n> Example config based on a working `2026.5.x` setup\n\nThis repo is a practical runbook for running OpenClaw day to day without burning money, exposing your gateway, or trusting random automation you did not inspect.\n\nIt is not official OpenClaw documentation.\nIt is not a universal best setup.\nIt is the way I run OpenClaw after enough broken configs, noisy agents, and avoidable risk to want something predictable.\n\n## What this is\n\n- A runbook for people who want OpenClaw to run for weeks, not minutes\n- Opinionated guidance on models, access, memory, automation, and guardrails\n- Tailscale-first for dashboard\u002Fcontrol access\n- Skeptical of third-party skills by default\n- Written from the post-honeymoon phase\n\n## What this is not\n\n- A beginner replacement for the official docs\n- A model leaderboard\n- A ClawHub install guide\n- A claim that my exact config is right for everyone\n\n## Access stance\n\nMy setup uses Tailscale as the normal access path, including when I am local. The Gateway stays loopback-bound, and Tailscale handles remote access.\n\nIf you do not want to sign up for Tailscale, keep OpenClaw local and use a messaging channel such as Telegram for remote use. Avoid public ports and casual LAN exposure unless you know exactly what boundary you are accepting.\n\n## Skills stance\n\nI do not recommend blindly installing third-party skills from ClawHub.\n\nUse ClawHub as a discovery and source-reading tool. Find an idea, inspect the source, then ask your agent to rebuild a local skill for your setup. That is slower than clicking install, but it is safer than trusting unknown code, broad tool assumptions, hidden behavior, or token-heavy abstractions.\n\nThe example config keeps `clawhub` disabled on purpose.\n\n## The guide\n\nThe main guide lives here:\n\n- [guide.md](.\u002Fguide.md)\n\nIt covers the current setup flow, Tailscale-first access, model routing, memory, automation, skills, and security.\n\n## Examples\n\nThe `examples\u002F` directory contains templates and references:\n\n- [sanitized-config.json](examples\u002Fsanitized-config.json) - Current sanitized config reference\n- [config-example-guide.md](examples\u002Fconfig-example-guide.md) - Config section reference\n- [agent-prompts.md](examples\u002Fagent-prompts.md) - Specialized agent examples\n- [spawning-patterns.md](examples\u002Fspawning-patterns.md) - Current `sessions_spawn` and subagent patterns\n- [heartbeat-example.md](examples\u002Fheartbeat-example.md) - Heartbeat checklist and `tasks:` pattern\n- [task-tracking-prompt.md](examples\u002Ftask-tracking-prompt.md) - Using OpenClaw's task ledger instead of an external black box\n- [security-hardening.md](examples\u002Fsecurity-hardening.md) - Security baseline and audit workflow\n- [security-quickstart.md](examples\u002Fsecurity-quickstart.md) - Prompts for applying basic guardrails\n- [security-patterns.md](examples\u002Fsecurity-patterns.md) - Prompt injection rules\n- [vps-setup.md](examples\u002Fvps-setup.md) - VPS setup with Tailscale as the default remote access path\n- [skill-builder-prompt.md](examples\u002Fskill-builder-prompt.md) - Prompt template for rebuilding local skills\n- [check-quotas.sh](examples\u002Fcheck-quotas.sh) - Optional quota check helper\n\n## Showcases\n\nThe `showcases\u002F` directory contains automation patterns you can adapt:\n\n- [daily-brief](showcases\u002Fdaily-brief.md) - Morning summary with weather, calendar, and tasks\n- [idea-pipeline](showcases\u002Fidea-pipeline.md) - Overnight research on captured ideas\n- [linkedin-drafter](showcases\u002Flinkedin-drafter.md) - Weekly draft generation\n- [tech-discoveries](showcases\u002Ftech-discoveries.md) - Curated tech news\n- [homelab-access](showcases\u002Fhomelab-access.md) - Safer remote SSH through Telegram confirmations\n- [agent-orchestrator](showcases\u002Fagent-orchestrator.md) - Route coding tasks to configured agents\u002Ftools\n- [coeus-knowledge-base](showcases\u002Fcoeus-knowledge-base.md) - Local semantic knowledge base example\n- [autonomous-operation](showcases\u002Fautonomous-operation.md) - Community-contributed health-check pattern\n- [claworc](showcases\u002Fclaworc.md) - Community-contributed review of an external control-plane project\n\nTreat showcases as starting points. Review tool access, channels, delivery targets, and model choices before running them unattended. Some showcases are community contributions or external project reviews; keep their attribution intact.\n\n## Share This\n\nIf this guide helped you, please consider:\n\n- sharing it with others who might find it useful;\n- linking back if you reference it in blog posts, videos, or other resources;\n- submitting your own showcases so others can learn from your setup.\n\nThis is a community resource. The more people contribute real working patterns, the better it gets.\n\n## Community resources\n\n- [OpenClaw Docs](https:\u002F\u002Fdocs.openclaw.ai) - Official documentation\n- [ClawHub](https:\u002F\u002Fclawhub.com) - Good for discovery and source inspection; not something I install from blindly\n- [OpenClaw GitHub](https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw) - Issues, releases, and source\n- [awesome-openclaw-usecases](https:\u002F\u002Fgithub.com\u002Fhesamsheikh\u002Fawesome-openclaw-usecases) - Real-world use cases and examples\n- [awesome-openclaw](https:\u002F\u002Fgithub.com\u002FSamurAIGPT\u002Fawesome-openclaw) - Curated tools and resources\n- [awesome-openclaw-skills](https:\u002F\u002Fgithub.com\u002FVoltAgent\u002Fawesome-openclaw-skills) - Community-contributed skills to inspect before rebuilding your own\n\n## Contributing\n\nContributions are welcome, but this is not a free-for-all.\n\nPlease read [CONTRIBUTING.md](.\u002FCONTRIBUTING.md) before opening issues or pull requests.\n\n## License\n\nMIT\n","这个项目是一个非官方的OpenClaw运行手册，旨在帮助用户在日常使用中避免不必要的开支、暴露网关或信任未经检查的自动化。它提供了关于模型选择、访问控制、内存管理、自动化设置和安全防护的具体建议，特别强调了Tailscale作为首选的远程访问方案，并对第三方技能持谨慎态度，推荐用户自行审查源码后重建本地技能。适合于希望长期稳定运行OpenClaw且重视安全性与成本控制的个人或团队使用。",2,"2026-06-11 04:08:45","high_star"]