[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NTAD8BM73J9RG8R4RTS7EW":3,"skill-same:01M6NTAD8BM73J9RG8R4RTS7EW":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":32,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6NTAD8BM73J9RG8R4RTS7EW","agent-self-scheduling",null,"Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fagent-self-scheduling\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"self","agent self scheduling","scheduling","unsafe","github","agent-orchestration","with","loops","critical","main","community","autonomous","schedule","cron","https","license","automation","orchestration","ai agent","codex","2026-11-10 10:12:30",false,"---\nname: agent-self-scheduling\ndescription: \"Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.\"\ncategory: agent-orchestration\nrisk: critical\nsource: community\nsource_repo: davidondrej\u002Fskills\nsource_type: community\ndate_added: \"2026-07-07\"\nauthor: davidondrej\ntags: [agents, scheduling, automation, cron]\ntools: [claude, codex]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Agent Self-Scheduling\n\n## When to Use\n\n- Use when the user asks for recurring, scheduled, heartbeat, or looped agent work.\n- Use when you need to choose between cron, external schedulers, hooks, or built-in agent scheduling.\n\nFirst question: does the agent have a built-in scheduler (Hermes → Camp B), or do you own the clock (everything else → Camp A)?\n\nUniversal floor: cron is 1 minute minimum (5-field expr, no seconds) — every camp. For sub-minute you MUST use a `while ...; sleep N; done` loop, a TS extension, or an event hook. Never put an LLM on a tight timer.\n\n## Camp A — one-shot agents, you own the clock\n\nThese run once and exit (amnesiac unless resumed). Schedule them externally.\n\n```bash\nclaude -p \"PROMPT\" --output-format json --allowedTools \"Read,Edit,Bash\"  # Claude Code\ncodex exec --json \"PROMPT\"                                                # Codex\npi run \"PROMPT\"                                                           # Pi\n```\n\nWrap in a clock:\n\n```bash\n# 1. cron (>= 1 min floor)\n*\u002F10 * * * * cd \u002Fpath\u002Fto\u002Fproject && pi run \"check X and report\" >> ~\u002Fagent.log 2>&1\n# 2. systemd timer (Linux, survives reboot, better logging) — OnUnitActiveSec=10min\n# 3. dumb loop (sub-minute, or no cron available)\nwhile true; do pi run \"check X\"; sleep 30; done\n```\n\nGotchas (each breaks unattended runs if ignored):\n- **Permissions hang forever.** Pass `--allowedTools` (Claude) or sandbox\u002Fauto-approve flags (Codex), or the run blocks on a prompt.\n- **Use JSON output** (`--output-format json` \u002F `--json`) so the wrapper parses results deterministically.\n- **Runs are amnesiac.** Resume (`codex exec resume --last`) or persist state to a file the next run reads.\n\nPi has NO built-in scheduler\u002Floop\u002Fheartbeat by design — external clock only (or a TS extension for agent-side timers).\n\n### cmux — orchestration only, NO scheduler\n\ncmux has no timer\u002Fwatch\u002Fcron. Three ways to loop it: orchestrator-driven (`send` → `sleep` → `read-screen` on your own clock), a dumb while-sleep wrapper, or — preferred — event-driven via `cmux notify` + OSC terminal hooks, which is cheaper and more responsive than polling. `read-screen` is non-interruptive, safe to poll.\n\nIf a loop checks another agent, send the user a one-line status each check: what the agent is doing, on track or not. (Claude Code may prefill a predicted next user message after finishing — that's Claude, not the user.)\n\n## Camp B — Hermes built-in scheduler\n\nHermes' gateway ticks every 60s and runs due jobs in fresh isolated sessions. State-check first:\n\n```bash\nhermes gateway install            # user-level ( --system to survive reboot)\nhermes cron create \"every 1h\" \"summarize new emails and report\" --skill himalaya\nhermes cron create \"0 9 * * *\" \"post daily standup\"      # cron expr\nhermes cron create \"30m\" \"one-shot reminder in 30 min\"   # one-shot delay\n```\n\nHermes-unique: **zero-token mode** (run a script, deliver stdout verbatim — use for watchdogs), **chaining** (`context_from` pipes one job's output into the next), **self-terminating loops**, and **loop safety** (scheduled sessions cannot create more cron jobs — don't schedule from inside a scheduled job). Each run is a fresh session: the prompt must carry all context.\n\n## Heartbeat pattern\n\nOne fast recurring tick gates many slower per-task checks: the tick reads a task list + per-task `last_run` timestamps and only acts on tasks that are due. In Hermes use a recurring job (zero-token mode when nothing's due); in Camp A use a while-sleep loop. Define active-hours, and stay silent when nothing is due — no empty noise.\n\n## Verify it fires (before reporting success)\n\n1. Camp A: log file grows after one interval, or run the wrapped command once by hand → clean JSON, exit 0.\n2. Camp B: `hermes cron list` shows the job + sane `next_run`; trigger a run-now to confirm delivery.\n3. Confirm permission\u002Fsandbox flags are present — the #1 silent failure is a hung permission prompt.\n4. Heartbeats: confirm a nothing-due tick stays silent.\n\n## Limitations\n\n- Adapted from `davidondrej\u002Fskills`; verify local paths, tools, credentials, and agent features before acting.\n- For commands, remote access, scheduling, browser automation, or file-changing workflows, get explicit user approval and confirm the target environment first.\n","# Agent Self-Scheduling\n\n## When to Use\n\n- Use when the user asks for recurring, scheduled, heartbeat, or looped agent work.\n- Use when you need to choose between cron, external schedulers, hooks, or built-in agent scheduling.\n\nFirst question: does the agent have a built-in scheduler (Hermes → Camp B), or do you own the clock (everything else → Camp A)?\n\nUniversal floor: cron is 1 minute minimum (5-field expr, no seconds) — every camp. For sub-minute you MUST use a `while ...; sleep N; done` loop, a TS extension, or an event hook. Never put an LLM on a tight timer.\n\n## Camp A — one-shot agents, you own the clock\n\nThese run once and exit (amnesiac unless resumed). Schedule them externally.\n\n```bash\nclaude -p \"PROMPT\" --output-format json --allowedTools \"Read,Edit,Bash\"  # Claude Code\ncodex exec --json \"PROMPT\"                                                # Codex\npi run \"PROMPT\"                                                           # Pi\n```\n\nWrap in a clock:\n\n```bash\n# 1. cron (>= 1 min floor)\n*\u002F10 * * * * cd \u002Fpath\u002Fto\u002Fproject && pi run \"check X and report\" >> ~\u002Fagent.log 2>&1\n# 2. systemd timer (Linux, survives reboot, better logging) — OnUnitActiveSec=10min\n# 3. dumb loop (sub-minute, or no cron available)\nwhile true; do pi run \"check X\"; sleep 30; done\n```\n\nGotchas (each breaks unattended runs if ignored):\n- **Permissions hang forever.** Pass `--allowedTools` (Claude) or sandbox\u002Fauto-approve flags (Codex), or the run blocks on a prompt.\n- **Use JSON output** (`--output-format json` \u002F `--json`) so the wrapper parses results deterministically.\n- **Runs are amnesiac.** Resume (`codex exec resume --last`) or persist state to a file the next run reads.\n\nPi has NO built-in scheduler\u002Floop\u002Fheartbeat by design — external clock only (or a TS extension for agent-side timers).\n\n### cmux — orchestration only, NO scheduler\n\ncmux has no timer\u002Fwatch\u002Fcron. Three ways to loop it: orchestrator-driven (`send` → `sleep` → `read-screen` on your own clock), a dumb while-sleep wrapper, or — preferred — event-driven via `cmux notify` + OSC terminal hooks, which is cheaper and more responsive than polling. `read-screen` is non-interruptive, safe to poll.\n\nIf a loop checks another agent, send the user a one-line status each check: what the agent is doing, on track or not. (Claude Code may prefill a predicted next user message after finishing — that's Claude, not the user.)\n\n## Camp B — Hermes built-in scheduler\n\nHermes' gateway ticks every 60s and runs due jobs in fresh isolated sessions. State-check first:\n\n```bash\nhermes gateway install            # user-level ( --system to survive reboot)\nhermes cron create \"every 1h\" \"summarize new emails and report\" --skill himalaya\nhermes cron create \"0 9 * * *\" \"post daily standup\"      # cron expr\nhermes cron create \"30m\" \"one-shot reminder in 30 min\"   # one-shot delay\n```\n\nHermes-unique: **zero-token mode** (run a script, deliver stdout verbatim — use for watchdogs), **chaining** (`context_from` pipes one job's output into the next), **self-terminating loops**, and **loop safety** (scheduled sessions cannot create more cron jobs — don't schedule from inside a scheduled job). Each run is a fresh session: the prompt must carry all context.\n\n## Heartbeat pattern\n\nOne fast recurring tick gates many slower per-task checks: the tick reads a task list + per-task `last_run` timestamps and only acts on tasks that are due. In Hermes use a recurring job (zero-token mode when nothing's due); in Camp A use a while-sleep loop. Define active-hours, and stay silent when nothing is due — no empty noise.\n\n## Verify it fires (before reporting success)\n\n1. Camp A: log file grows after one interval, or run the wrapped command once by hand → clean JSON, exit 0.\n2. Camp B: `hermes cron list` shows the job + sane `next_run`; trigger a run-now to confirm delivery.\n3. Confirm permission\u002Fsandbox flags are present — the #1 silent failure is a hung permission prompt.\n4. Heartbeats: confirm a nothing-due tick stays silent.\n\n## Limitations\n\n- Adapted from `davidondrej\u002Fskills`; verify local paths, tools, credentials, and agent features before acting.\n- For commands, remote access, scheduling, browser automation, or file-changing workflows, get explicit user approval and confirm the target environment first.\n",{"name":5,"risk":31,"tags":48,"tools":50,"author":52,"source":33,"license":14,"category":28,"date_added":53,"description":7,"source_repo":54,"source_type":33,"license_source":55},[49,25,39,36],"agents",[51,42],"claude","davidondrej","2026-07-07","davidondrej\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fagent-self-scheduling","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill agent-self-scheduling",{"tool":67,"command":68},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill agent-self-scheduling",{"tool":70,"command":71},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill agent-self-scheduling","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fagent-self-scheduling\u002FSKILL.md",true,[],[76,102,124,145,173,197],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":85,"publishedAt":43},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[86,87,88,89,90,91,78,92,93,94,95,96,33,32,97,31,98,99,100,101],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":43},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[109,110,111,112,113,40,114,115,116,117,118,119,120,96,121,33,122,123,31,28],"delegate","zcode","zcode delegate","review","cli","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":43},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[131,132,133,134,27,42,135,38,37,136,137,138,139,33,32,140,141,142,143,144],"transcript","youtube transcript","youtube","safe","research","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":162,"publishedAt":43},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[151,154,157],{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":158,"categoryName":159,"taxonomyType":160,"taxonomyTypeDesc":161},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[131,132,133,163,134,164,27,42,38,165,166,167,168,137,169,33,32,170,171,172],"youtube transcript skills","gemini","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":183,"publishedAt":43},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[179,182],{"categoryNo":180,"categoryName":181,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":155,"categoryName":156,"taxonomyType":20,"taxonomyTypeDesc":21},[133,184,185,113,134,186,187,188,189,38,167,190,191,192,193,32,194,140,195,196],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":43},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[203],{"categoryNo":152,"categoryName":153,"taxonomyType":20,"taxonomyTypeDesc":21},[205,133,206,207,134,164,165,208,209,166,167,168,137,210,169,33,32,170,211,143],"youtube full","full","google","server","dlp","credits","automatic"]