[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DD9GR5YR84R8FHGVYTXFRT":3,"skill-same:01M6DD9GR5YR84R8FHGVYTXFRT":64},{"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":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DD9GR5YR84R8FHGVYTXFRT","codex-databricks-fanout",null,"Use when fanning out Codex CLI agents onto Databricks — running many parallel Codex\u002FLLM work units on job clusters, scaling past a local RAM ceiling, or deciding between Databricks \u002F local \u002F Modal \u002F RunPod for a large agent fan-out. Carries the measured constraints from a 608-unit production run + a 48-unit auth-research re-prove so a session does not re-derive them wrong.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.claude\u002Fskills\u002Fcodex-databricks-fanout\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"codex","codex databricks fanout","fanout","databricks","auth","codex cli","run","Production","modal","parallel","work","session","use","research","runpod","units","local","scaling","cli agents","cli","2026-11-10 10:12:30",false,"---\nname: codex-databricks-fanout\ndescription: Use when fanning out Codex CLI agents onto Databricks — running many parallel Codex\u002FLLM work units on job clusters, scaling past a local RAM ceiling, or deciding between Databricks \u002F local \u002F Modal \u002F RunPod for a large agent fan-out. Carries the measured constraints from a 608-unit production run + a 48-unit auth-research re-prove so a session does not re-derive them wrong.\n---\n\n# Codex fan-out on Databricks\n\nEverything below was **measured on 2026-07-19** on workspace `bolt-datascience`\n(`costin.ionescu@bolt.eu` \u002F profile DEFAULT). Facts marked MEASURED are not to be\nre-litigated from first principles — a session reasoning from scratch about this\ngets the binding constraint wrong (see §1).\n\n## 1. The constraint everyone guesses wrong\n\nA session planning this will typically assert:\n\n> *\"Databricks is Spark\u002FJobs, not Codex CLI hosts. Codex OAuth + auth.json must NOT fan out to N\n> workers — that's the dual-writer failure mode.\"*\n\n**Both halves are wrong as stated.**\n\n**Databricks job nodes host Codex CLI fine.** The runtime is ordinary Linux. You install\nnode + `@openai\u002Fcodex` (or the official tarball) and run `codex exec`. It is not\n*Spark-native*, but \"not a Codex host\" is false — **608 units** (mega-audit) and a\n**48-unit auth-research re-prove (run 343617464274709)** completed this way.\n\n**One shared `auth.json` served 180 concurrent Codex processes on one node with zero auth\ncorruption.** MEASURED, batch-01. Of 180, exactly 120 failed and **every single failure was\n`429 Too Many Requests — exceeded retry limit`**, all dying in a 37–41s band. They fired at t=0,\nhit the same rate window, burned codex's internal retries together, and gave up together. The 60\nsurvivors were pristine. The node still had **228.9 GB free**.\n\nThat is a **thundering herd against the API rate limit**, not a capacity problem and not an auth\nrace. The real binding constraint at high fan-out is **arrival rate**, and the fix is a stagger:\n\n### What is NOT proven (do not overclaim)\n### 2. Account-level facts (MEASURED)\n### Required submit shape (copy this)\n### 3. Batching is mandatory\n### 4. Classify units before dispatch\n### 5. Getting results back\n### 6. Completion is an AND-gate, never an exit code\n### 7. Choosing the execution model\n### 8. Pre-flight checklist\n### 9. Harness paths (this workspace)\n","# Codex fan-out on Databricks\n\nEverything below was **measured on 2026-07-19** on workspace `bolt-datascience`\n(`costin.ionescu@bolt.eu` \u002F profile DEFAULT). Facts marked MEASURED are not to be\nre-litigated from first principles — a session reasoning from scratch about this\ngets the binding constraint wrong (see §1).\n\n## 1. The constraint everyone guesses wrong\n\nA session planning this will typically assert:\n\n> *\"Databricks is Spark\u002FJobs, not Codex CLI hosts. Codex OAuth + auth.json must NOT fan out to N\n> workers — that's the dual-writer failure mode.\"*\n\n**Both halves are wrong as stated.**\n\n**Databricks job nodes host Codex CLI fine.** The runtime is ordinary Linux. You install\nnode + `@openai\u002Fcodex` (or the official tarball) and run `codex exec`. It is not\n*Spark-native*, but \"not a Codex host\" is false — **608 units** (mega-audit) and a\n**48-unit auth-research re-prove (run 343617464274709)** completed this way.\n\n**One shared `auth.json` served 180 concurrent Codex processes on one node with zero auth\ncorruption.** MEASURED, batch-01. Of 180, exactly 120 failed and **every single failure was\n`429 Too Many Requests — exceeded retry limit`**, all dying in a 37–41s band. They fired at t=0,\nhit the same rate window, burned codex's internal retries together, and gave up together. The 60\nsurvivors were pristine. The node still had **228.9 GB free**.\n\nThat is a **thundering herd against the API rate limit**, not a capacity problem and not an auth\nrace. The real binding constraint at high fan-out is **arrival rate**, and the fix is a stagger:\n\n### What is NOT proven (do not overclaim)\n### 2. Account-level facts (MEASURED)\n### Required submit shape (copy this)\n### 3. Batching is mandatory\n### 4. Classify units before dispatch\n### 5. Getting results back\n### 6. Completion is an AND-gate, never an exit code\n### 7. Choosing the execution model\n### 8. Pre-flight checklist\n### 9. Harness paths (this workspace)\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.claude\u002Fskills\u002Fcodex-databricks-fanout","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill codex-databricks-fanout",{"tool":56,"command":57},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill codex-databricks-fanout",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill codex-databricks-fanout","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.claude\u002Fskills\u002Fcodex-databricks-fanout\u002FSKILL.md",true,[],[65,86,116,143,157,172],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":39},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[72,73,74,75,76,77,78,79,80,31,81,82,83,84,85],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":97,"publishedAt":39},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[98,99,100,101,102,103,104,105,106,107,108,109,110,111,31,112,113,35,114,115],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","do","MCP",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":128,"publishedAt":39},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[122,125],{"categoryNo":123,"categoryName":124,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":126,"categoryName":127,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000008","测试与质量",[129,130,131,132,133,134,135,136,137,138,99,139,140,141,142],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":39},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[145,150,151,152,153,154,155,156],"setup","report","project","installation","project setup","issues","state",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":39},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[163],{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},[159,165,77,166,167,168,31,169,29,170,171],"start issue","issue","ready","work on issue","user","work on","development",{"skillNo":173,"name":150,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":39},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[150,152,35,178,154,179],"files","interactive"]