[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NT46MQA5EBGTMYRS06HD4M":3,"skill-same:01M6NT46MQA5EBGTMYRS06HD4M":55},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M6NT46MQA5EBGTMYRS06HD4M","agent-context-isolation",null,"Agent Context Isolation","rubicanjr\u002FFinCognis","rubicanjr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234912519?v=4","01M6NT156NND8J474G34SB3923","Rubi","01M6NT15B70RWXE1N3YV0BZY8A",0,"MIT","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fagent-context-isolation\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],"context","isolation","agent context isolation","false","2026-11-10 10:12:30",false,"---\nname: agent-context-isolation\ndescription: Agent Context Isolation\nuser-invocable: false\n---\n\n# Agent Context Isolation\n\nPrevent agent output from polluting the main context window.\n\n## Rules\n\n### 1. Use Background Agents with File-Based Coordination\n```\n# RIGHT - background agent writes to file, main reads file\nTask(subagent_type=\"...\", run_in_background=true, prompt=\"... Output to: \u002Fpath\u002Fto\u002Ffile.md\")\n\n# WRONG - foreground agent dumps full transcript into main context\nTask(subagent_type=\"...\", run_in_background=false)\n```\n\nBackground agents with `run_in_background=true` isolate their context. Have them write results to files in `.claude\u002Fcache\u002Fagents\u002F\u003Cagent-type>\u002F`.\n\n### 2. Never Use TaskOutput to Retrieve Results\n```\n# WRONG - dumps entire transcript (70k+ tokens) into context\nTaskOutput(task_id=\"\u003Cid>\")\nTaskOutput(task_id=\"\u003Cid>\", block=true)\n\n# RIGHT - check expected output files\nBash(\"ls -la .claude\u002Fcache\u002Fagents\u002F\u003Cagent-type>\u002F\")\nBash(\"bun test\")  # verify with tests\n```\n\nTaskOutput returns the full agent transcript. Always use file-based coordination instead.\n\n### 3. Monitor Agent Progress via System Reminders\n```\n# System reminders come automatically:\n# \"Agent a42a16e progress: 6 new tools used, 88914 new tokens\"\n\n# To detect completion:\n# - Watch for progress reminders to stop arriving\n# - Poll for expected output files: find .claude\u002Fcache\u002Fagents -name \"*.md\" -mmin -5\n# - Check task output file size growth: wc -c \u002Ftmp\u002Fclaude\u002F...\u002Ftasks\u002F\u003Cid>.output\n```\n\n**Stuck agent detection:**\n1. Progress reminders stop arriving\n2. Task output file size stops growing\n3. Expected output file not created after reasonable time\n\n### 4. Verify with Tests, Not Output\nAfter agent work:\n1. Run the test suite directly: `bun test`\n2. Report pass\u002Ffail counts\n3. Only investigate failures if tests fail\n\n### 5. File-Based Agent Pipeline Pattern\n```\nResearch agent → .claude\u002Fcache\u002Fagents\u002Foracle\u002Foutput.md\n                          ↓\nPlan agent → .claude\u002Fcache\u002Fagents\u002Fplan-agent\u002Foutput.md (reads research)\n                          ↓\nValidate agent → .claude\u002Fcache\u002Fagents\u002Fvalidate-agent\u002Foutput.md (reads plan)\n                          ↓\nImplement agent → src\u002Fmodule.ts (reads validated plan)\n```\n\nEach agent reads the previous agent's file output, not TaskOutput.\n\n## Why This Matters\n\nAgent context isolation preserves the main conversation's context budget. Reading agent outputs via TaskOutput floods context, causing:\n- Mid-conversation compaction\n- Lost context about user's original request\n- Repeated explanations needed\n\n## Source\n- Session where TaskOutput flooded 70k+ tokens into main context\n- Session 2026-01-01: Successfully used background agents with file-based coordination for SDK Phase 3\n","# Agent Context Isolation\n\nPrevent agent output from polluting the main context window.\n\n## Rules\n\n### 1. Use Background Agents with File-Based Coordination\n```\n# RIGHT - background agent writes to file, main reads file\nTask(subagent_type=\"...\", run_in_background=true, prompt=\"... Output to: \u002Fpath\u002Fto\u002Ffile.md\")\n\n# WRONG - foreground agent dumps full transcript into main context\nTask(subagent_type=\"...\", run_in_background=false)\n```\n\nBackground agents with `run_in_background=true` isolate their context. Have them write results to files in `.claude\u002Fcache\u002Fagents\u002F\u003Cagent-type>\u002F`.\n\n### 2. Never Use TaskOutput to Retrieve Results\n```\n# WRONG - dumps entire transcript (70k+ tokens) into context\nTaskOutput(task_id=\"\u003Cid>\")\nTaskOutput(task_id=\"\u003Cid>\", block=true)\n\n# RIGHT - check expected output files\nBash(\"ls -la .claude\u002Fcache\u002Fagents\u002F\u003Cagent-type>\u002F\")\nBash(\"bun test\")  # verify with tests\n```\n\nTaskOutput returns the full agent transcript. Always use file-based coordination instead.\n\n### 3. Monitor Agent Progress via System Reminders\n```\n# System reminders come automatically:\n# \"Agent a42a16e progress: 6 new tools used, 88914 new tokens\"\n\n# To detect completion:\n# - Watch for progress reminders to stop arriving\n# - Poll for expected output files: find .claude\u002Fcache\u002Fagents -name \"*.md\" -mmin -5\n# - Check task output file size growth: wc -c \u002Ftmp\u002Fclaude\u002F...\u002Ftasks\u002F\u003Cid>.output\n```\n\n**Stuck agent detection:**\n1. Progress reminders stop arriving\n2. Task output file size stops growing\n3. Expected output file not created after reasonable time\n\n### 4. Verify with Tests, Not Output\nAfter agent work:\n1. Run the test suite directly: `bun test`\n2. Report pass\u002Ffail counts\n3. Only investigate failures if tests fail\n\n### 5. File-Based Agent Pipeline Pattern\n```\nResearch agent → .claude\u002Fcache\u002Fagents\u002Foracle\u002Foutput.md\n                          ↓\nPlan agent → .claude\u002Fcache\u002Fagents\u002Fplan-agent\u002Foutput.md (reads research)\n                          ↓\nValidate agent → .claude\u002Fcache\u002Fagents\u002Fvalidate-agent\u002Foutput.md (reads plan)\n                          ↓\nImplement agent → src\u002Fmodule.ts (reads validated plan)\n```\n\nEach agent reads the previous agent's file output, not TaskOutput.\n\n## Why This Matters\n\nAgent context isolation preserves the main conversation's context budget. Reading agent outputs via TaskOutput floods context, causing:\n- Mid-conversation compaction\n- Lost context about user's original request\n- Repeated explanations needed\n\n## Source\n- Session where TaskOutput flooded 70k+ tokens into main context\n- Session 2026-01-01: Successfully used background agents with file-based coordination for SDK Phase 3\n",{"name":5,"description":7,"user-invocable":29},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fagent-context-isolation","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis","https:\u002F\u002Fgithub.com\u002Frubicanjr","linktr.ee\u002Ffinanskodu","Industrial Engineer & CIO @FinansKodu. Architecting AI-driven financial agents and autonomous workflows. 🏗️ Building systems, not just prompts.","2026-06-09 13:50:15",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add rubicanjr\u002FFinCognis --skill agent-context-isolation",{"tool":47,"command":48},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill agent-context-isolation",{"tool":50,"command":51},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill agent-context-isolation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fagent-context-isolation\u002FSKILL.md",true,[],[56,73,81,101,131,150],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":63,"publishedAt":28},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router","Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[62],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[64,65,66,67,68,69,70,71,72],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":28},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[75,80,27],"verification",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":90,"publishedAt":28},"01M6NWS0XW9CVQZBDA1EGW0TWC","websocket-patterns","Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwebsocket-patterns\u002Fskill.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[91,92,93,94,95,96,97,98,99,100],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":111,"publishedAt":28},"01M6NWRDQDX9ZNETAWRRMQWV52","visual-verdict","Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS\u002FREVISE\u002FFAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[107,110],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[112,113,114,115,116,117,118,119,120,121,122,123,124,94,125,126,127,128,129,130],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":28},"01M6NWR8HSNRS7MNDK2J02QYMN","verification-loop","Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[138,139,80,140,141,142,143,144,145,146,147,148,149],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"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":156,"publishedAt":28},"01M6NWR4HHSFR0VR5EXFRWA747","vector-db-patterns","Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvector-db-patterns\u002Fskill.md",[],[157,158,159,160,92,161,162,163,164,98,165,166,167,168,169,121,170,171],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]