[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CR3GF4C0F2HQ3JBQW2S16Y":3,"skill-same:01M6CR3GF4C0F2HQ3JBQW2S16Y":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6CR3GF4C0F2HQ3JBQW2S16Y","codex-orchestrate",null,"Orchestrate a fleet of parallel `codex exec` workers with you as supervisor — one per isolated git worktree, dispatched headless, each verified INDEPENDENTLY, then PR\u002Fmerge. The manual \"codex-ultracode\" fan-out pattern with the hard gotchas baked in (stdin blocking, background tracking, don't-trust-self-reports, writer isolation). Triggers: orchestrate codex, codex workers\u002Ffleet, spawn codex, delegate to codex in parallel, manual ultracode, 开 codex 小弟, 派 codex worker — NOT for a single cross-vendor opinion (second-opinion-codex agent) or web-UI worker decomposition (\u002Forchestrate).","shenxingy\u002FClade","shenxingy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F89829751?v=4","01M6CQXHTV3WQZJMG0JXD93MEK","Xingyu (Alex) Shen","01M6CQXHYCTGPJ5HD8Z7MD4Q5P",10,"MIT","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fconfigs\u002Fskills\u002Fcodex-orchestrate\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"codex orchestrate","codex","orchestrate","pattern","decomposition","ultracode","self","codex exec","you","worker","codex agent","headless","git","spawn","merge","worktree","git worktree","reports","delegate","writer","2026-11-10 10:12:30",false,"---\nname: codex-orchestrate\ndescription: \"Orchestrate a fleet of parallel `codex exec` workers with you as supervisor — one per isolated git worktree, dispatched headless, each verified INDEPENDENTLY, then PR\u002Fmerge. The manual \\\"codex-ultracode\\\" fan-out pattern with the hard gotchas baked in (stdin blocking, background tracking, don't-trust-self-reports, writer isolation). Triggers: orchestrate codex, codex workers\u002Ffleet, spawn codex, delegate to codex in parallel, manual ultracode, 开 codex 小弟, 派 codex worker — NOT for a single cross-vendor opinion (second-opinion-codex agent) or web-UI worker decomposition (\u002Forchestrate).\"\n---\n\n# Codex Orchestrate — you supervise a fleet of `codex exec` workers\n\nUse when the user wants Codex to actually DO work at scale (implement N gaps, research N sources, review N dimensions) and you drive it — the manual equivalent of Codex's native `ultra`\u002Fmulti_agent, but with no slot cap and with YOUR verification gate on every result.\n\nRead `prompt.md` for the full loop, the exact dispatch command, and the verification checklist. The four rules that make it work (each learned from a real failure):\n\n1. **`\u003C \u002Fdev\u002Fnull`** on every `codex exec` — it blocks on stdin EOF otherwise, even with the prompt as an arg, and hangs until timeout.\n2. **One isolated git worktree per worker** off the latest main — parallel writers to shared build\u002Ftest state race; core-engine changes merge **sequentially** so each builds on the last.\n3. **Verify independently — never trust the worker's self-report.** Re-run the tests yourself (a worker reported \"996 passed\"; the real number was 995 + 1 real failure). For core-engine changes run the FULL suite, not just the new test.\n4. **Dispatch via a tracked background call** (`run_in_background`), not `&` inside another command, or you lose the completion signal.\n\nOne more, observed on codex-cli 0.167.0 rather than learned from a failure: **`codex exec resume` works in the directory you run it from, not the session's**. Put `-C \u003Cworktree>` before `resume`, or the follow-up edits wherever you stand. To cancel, signal the session the dispatch records in `\u003Cpgid-file>`. `prompt.md` § Steer, cancel, follow up has both.\n","# Codex Orchestrate — you supervise a fleet of `codex exec` workers\n\nUse when the user wants Codex to actually DO work at scale (implement N gaps, research N sources, review N dimensions) and you drive it — the manual equivalent of Codex's native `ultra`\u002Fmulti_agent, but with no slot cap and with YOUR verification gate on every result.\n\nRead `prompt.md` for the full loop, the exact dispatch command, and the verification checklist. The four rules that make it work (each learned from a real failure):\n\n1. **`\u003C \u002Fdev\u002Fnull`** on every `codex exec` — it blocks on stdin EOF otherwise, even with the prompt as an arg, and hangs until timeout.\n2. **One isolated git worktree per worker** off the latest main — parallel writers to shared build\u002Ftest state race; core-engine changes merge **sequentially** so each builds on the last.\n3. **Verify independently — never trust the worker's self-report.** Re-run the tests yourself (a worker reported \"996 passed\"; the real number was 995 + 1 real failure). For core-engine changes run the FULL suite, not just the new test.\n4. **Dispatch via a tracked background call** (`run_in_background`), not `&` inside another command, or you lose the completion signal.\n\nOne more, observed on codex-cli 0.167.0 rather than learned from a failure: **`codex exec resume` works in the directory you run it from, not the session's**. Put `-C \u003Cworktree>` before `resume`, or the follow-up edits wherever you stand. To cancel, signal the session the dispatch records in `\u003Cpgid-file>`. `prompt.md` § Steer, cancel, follow up has both.\n",{"name":5,"description":7},"main","25302dbcb683029b8a4d75325ae7758944b27114","configs\u002Fskills\u002Fcodex-orchestrate",6,"https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade","https:\u002F\u002Falexshen.dev\u002Fen\u002Fblog\u002Fclade","https:\u002F\u002Fgithub.com\u002Fshenxingy","https:\u002F\u002Falexshen.dev\u002F","Founding Engineer @ Scam AI | ECE @ Duke University | Data Science @ Duke Kunshan University","2026-11-10 11:54:03",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add shenxingy\u002FClade --skill codex-orchestrate",{"tool":65,"command":66},"bunx","bunx skills add shenxingy\u002FClade --skill codex-orchestrate",{"tool":68,"command":69},"pnpm","pnpm dlx skills add shenxingy\u002FClade --skill codex-orchestrate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fconfigs\u002Fskills\u002Fcodex-orchestrate\u002FSKILL.md",true,[73],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"prompt.md","REFERENCE","参考文档",14596,"https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fconfigs\u002Fskills\u002Fcodex-orchestrate\u002Fprompt.md",[80,97,130,150,176,193],{"skillNo":81,"name":39,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":44},"01M6FNPBA3494GF2W7V4MMAKG3","Create or inspect runtime-adaptive isolated Git workspaces with explicit ownership and delivery routing","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fworktree\u002FSKILL.md",[85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[39,87,88,89,90,91,92,93,94,36,95,96],"adaptive","inspect","with","ownership","delivery routing","runtime","delivery","workspaces","routing","create",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":109,"publishedAt":44},"01M6FNP75BY8CS006EWGN29FM0","web-search","Route online research and URL reading to native tools or TinyFish MCP\u002FAPI; prepare targeted requests, handle progress and failures, and check returned evidence. Applies to web search, fetching, and bulk collection; excludes repository\u002Ffile search.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fweb-search\u002FSKILL.md",[103,104],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"web search","search","web","repository","file","research","MCP","requests","collection","reading","URL","native","bulk","progress","file search","route","tinyfish","evidence","check","api",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":137,"publishedAt":44},"01M6FNP2616DRTZRSZJQM3HPHY","verify","Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Codex built-in \u002Fverify (which runs the app to observe a single change working) — this one walks the AGENTS.md \"Features (Behavior Anchors)\" list.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fverify\u002FSKILL.md",[136],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[132,138,139,140,141,142,143,144,145,146,147,148,149,25],"app","single","features","which","interaction","tests","project","observe","autonomous","behavior","list","change",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":157,"publishedAt":44},"01M6FNNX95R9H29BNERFY15704","tasks","Coordinate dependency-aware project tasks across independent Codex, Codex, Kimi and human sessions using Beads. Use for shared plans, claiming work, task handoffs, acceptance and agent monitoring snapshots.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Ftasks\u002FSKILL.md",[156],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[152,158,159,160,144,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,25],"for","plans","work","shared","across","human","task","coordinate","kimi","snapshots","agent monitoring","dependency","use","using beads","beads","monitoring","acceptance","sessions",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":44},"01M6FNNTAD1BCZX5Q9TC55MZCH","sync","End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run \u002Fcommit after to commit everything)","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fsync\u002FSKILL.md",[182],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[178,184,185,186,187,188,189,190,123,191,192],"session","run","documentation","commit","only","documentation sync","updates","end","todo",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":200,"publishedAt":44},"01M6FNNPTR5H23MD3849E66WYA","status","Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime\u002Fprovider\u002Fmodel, or stuck-work checks.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fstatus\u002FSKILL.md",[199],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[195,92,201,202,158,190,203,204,123,205,93,206,207,170,208,160,209,210,36,211],"running","limits","usage","now","active","show","provider","snapshot","model","execution","identity"]