{ "schemaVersion": "1.0", "item": { "slug": "agent-orchestrator-molter", "name": "Agent Orchestrator", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/variable190/agent-orchestrator-molter", "canonicalUrl": "https://clawhub.ai/variable190/agent-orchestrator-molter", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-orchestrator-molter", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-orchestrator-molter", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CHANGELOG.md", "CONVENTION.md", "PUBLISHING.md", "README.md", "SECURITY.md", "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/agent-orchestrator-molter" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/agent-orchestrator-molter", "agentPageUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "agent-orchestrator", "body": "Multi-agent orchestration for OpenClaw. Implements 5 proven patterns for coordinating multiple AI agents: Work Crew, Supervisor, Pipeline, Expert Council, and Auto-Routing.\n\nUSE WHEN:\n\nA task can be parallelized for speed or redundancy (Work Crew)\nComplex tasks need dynamic planning and delegation (Supervisor)\nWork follows a predictable sequence of stages (Pipeline)\nCross-domain input is needed from multiple specialists (Expert Council)\nMixed task types need automatic routing to appropriate specialists (Auto-Routing)\nResearch tasks require breadth-first exploration of multiple angles\nHigh-stakes decisions need confidence through multiple perspectives\n\nDON'T USE WHEN:\n\nSimple tasks that fit in one agent's context window (use main session instead)\nSequential tasks with no parallelization opportunity (use regular tool calls)\nOne-shot deterministic tasks (use single agent)\nTasks requiring real-time inter-agent conversation (this uses async spawning)\nTasks where 15x token cost cannot be justified\nQuick/simple tasks where coordination overhead exceeds benefit\n\nOutputs:\n\nAggregated results from multiple parallel agents\nSynthesized consensus recommendations\nRouting decisions to appropriate specialists\nStructured output from staged processing" }, { "title": "Decision Matrix", "body": "PatternUse WhenAvoid WhencrewSame task from multiple angles, verification, research breadthResults cannot be easily compared/mergedsuperviseDynamic decomposition needed, complex planningFixed workflow, simple delegationpipelineWell-defined sequential stages, content creationPath needs runtime adaptationcouncilCross-domain expertise, risk assessment, policy reviewSingle-domain task, need fast consensusrouteMixed workload types, automatic classificationTask type is already known" }, { "title": "Auto-Routing Pattern", "body": "The route command analyzes tasks and automatically classifies them by type, then routes to the appropriate specialist:\n\n# Basic routing\nclaw agent-orchestrator route --task \"Write Python parser\"\n\n# With custom specialist pool\nclaw agent-orchestrator route \\\n --task \"Analyze data and create report\" \\\n --specialists \"analyst,data,writer\"\n\n# Force specific specialist\nclaw agent-orchestrator route \\\n --task \"Something complex\" \\\n --force coder" }, { "title": "Confidence Thresholds", "body": "High confidence (>0.85): Auto-route immediately\nGood confidence (0.7-0.85): Propose with confirmation option\nModerate confidence (0.5-0.7): Show top alternatives\nLow confidence (<0.5): Request clarification\n\nAvailable specialists: coder, researcher, writer, analyst, planner, reviewer, creative, data, devops, support" }, { "title": "Common Workflows", "body": "# Parallel research with consensus\nclaw agent-orchestrator crew \\\n --task \"Research Bitcoin Lightning 2026 adoption\" \\\n --agents 4 \\\n --perspectives technical,business,security,competitors \\\n --converge consensus\n\n# Best-of redundancy for critical analysis\nclaw agent-orchestrator crew \\\n --task \"Audit this smart contract for vulnerabilities\" \\\n --agents 3 \\\n --converge best-of\n\n# Supervisor-managed code review\nclaw agent-orchestrator supervise \\\n --task \"Refactor authentication module\" \\\n --workers coder,reviewer,tester \\\n --strategy adaptive\n\n# Staged content pipeline\nclaw agent-orchestrator pipeline \\\n --stages research,draft,review,finalize \\\n --input \"topic: AI agent adoption trends\"\n\n# Expert council for decision\nclaw agent-orchestrator council \\\n --question \"Should we publish this blog post about unreleased features?\" \\\n --experts skeptic,ethicist,strategist \\\n --converge consensus \\\n --rounds 2\n\n# Auto-route mixed tasks\nclaw agent-orchestrator route \\\n --task \"Write Python function to analyze CSV data\" \\\n --specialists coder,researcher,writer,analyst\n\n# Force route to specific specialist\nclaw agent-orchestrator route \\\n --task \"Debug authentication error\" \\\n --force coder \\\n --confidence-threshold 0.9\n\n# Route and output as JSON for scripting\nclaw agent-orchestrator route \\\n --task $TASK \\\n --format json \\\n --specialists \"coder,data,analyst\"" }, { "title": "Negative Examples", "body": "DON'T: Use crew for simple single-answer questions\n\n# WRONG: Wasteful for simple facts\nclaw agent-orchestrator crew --task \"What is 2+2?\" --agents 3\n\n# RIGHT: Use main session directly\nWhat is 2+2?\n\nDON'T: Use supervise when pipeline suffices\n\n# WRONG: Over-engineering fixed workflows\nclaw agent-orchestrator supervise --task \"Draft, edit, publish\"\n\n# RIGHT: Use pipeline for fixed sequences\nclaw agent-orchestrator pipeline --stages draft,edit,publish\n\nDON'T: Route when task type is obvious\n\n# WRONG: Unnecessary classification overhead\nclaw agent-orchestrator route --task \"Write Python code\"\n\n# RIGHT: Direct to appropriate specialist\nclaw agent-orchestrator crew --pattern code --task \"Write Python code\"\n\nDON'T: Use multi-agent for very small context tasks\n\n# WRONG: Coordination overhead exceeds value\nclaw agent-orchestrator crew --task \"Fix typo\" --agents 2\n\n# RIGHT: Single agent or direct edit\nedit file.py \"typo\" \"correct\"" }, { "title": "Token Cost Warning", "body": "Multi-agent patterns use approximately 15x more tokens than single-agent interactions. Use only for high-value tasks where quality improvement justifies the cost. See Anthropic research: token usage explains 80% of performance variance in complex tasks." }, { "title": "Dependencies", "body": "Python 3.8+\nOpenClaw sessions_spawn capability\nOpenClaw sessions_list capability\nOpenClaw sessions_history capability" }, { "title": "Files", "body": "__main__.py - CLI entry point\ncrew.py - Work Crew pattern implementation\nsupervise.py - Supervisor pattern (Phase 2)\ncouncil.py - Expert Council pattern (Phase 2)\npipeline.py - Pipeline pattern (Phase 2)\nroute.py - Auto-Routing pattern (Phase 2)\nutils.py - Shared utilities for session management" }, { "title": "Status", "body": "MVP: Work Crew pattern implemented\nPhase 2: 100% Complete\n\n Supervisor pattern implemented - dynamic task decomposition and worker delegation\n Pipeline pattern implemented - sequential staged processing with validation gates\n Council pattern implemented - multi-expert deliberation with convergence methods\n Route pattern implemented - intelligent task classification and specialist routing" }, { "title": "References", "body": "Anthropic Multi-Agent Research System\nLangGraph Supervisor Pattern\nCrewAI Framework\nAutoGen Conversational Agents" } ], "body": "agent-orchestrator\n\nMulti-agent orchestration for OpenClaw. Implements 5 proven patterns for coordinating multiple AI agents: Work Crew, Supervisor, Pipeline, Expert Council, and Auto-Routing.\n\nUSE WHEN:\n\nA task can be parallelized for speed or redundancy (Work Crew)\nComplex tasks need dynamic planning and delegation (Supervisor)\nWork follows a predictable sequence of stages (Pipeline)\nCross-domain input is needed from multiple specialists (Expert Council)\nMixed task types need automatic routing to appropriate specialists (Auto-Routing)\nResearch tasks require breadth-first exploration of multiple angles\nHigh-stakes decisions need confidence through multiple perspectives\n\nDON'T USE WHEN:\n\nSimple tasks that fit in one agent's context window (use main session instead)\nSequential tasks with no parallelization opportunity (use regular tool calls)\nOne-shot deterministic tasks (use single agent)\nTasks requiring real-time inter-agent conversation (this uses async spawning)\nTasks where 15x token cost cannot be justified\nQuick/simple tasks where coordination overhead exceeds benefit\n\nOutputs:\n\nAggregated results from multiple parallel agents\nSynthesized consensus recommendations\nRouting decisions to appropriate specialists\nStructured output from staged processing\nDecision Matrix\nPattern\tUse When\tAvoid When\ncrew\tSame task from multiple angles, verification, research breadth\tResults cannot be easily compared/merged\nsupervise\tDynamic decomposition needed, complex planning\tFixed workflow, simple delegation\npipeline\tWell-defined sequential stages, content creation\tPath needs runtime adaptation\ncouncil\tCross-domain expertise, risk assessment, policy review\tSingle-domain task, need fast consensus\nroute\tMixed workload types, automatic classification\tTask type is already known\nAuto-Routing Pattern\n\nThe route command analyzes tasks and automatically classifies them by type, then routes to the appropriate specialist:\n\n# Basic routing\nclaw agent-orchestrator route --task \"Write Python parser\"\n\n# With custom specialist pool\nclaw agent-orchestrator route \\\n --task \"Analyze data and create report\" \\\n --specialists \"analyst,data,writer\"\n\n# Force specific specialist\nclaw agent-orchestrator route \\\n --task \"Something complex\" \\\n --force coder\n\nConfidence Thresholds\nHigh confidence (>0.85): Auto-route immediately\nGood confidence (0.7-0.85): Propose with confirmation option\nModerate confidence (0.5-0.7): Show top alternatives\nLow confidence (<0.5): Request clarification\n\nAvailable specialists: coder, researcher, writer, analyst, planner, reviewer, creative, data, devops, support\n\nCommon Workflows\n# Parallel research with consensus\nclaw agent-orchestrator crew \\\n --task \"Research Bitcoin Lightning 2026 adoption\" \\\n --agents 4 \\\n --perspectives technical,business,security,competitors \\\n --converge consensus\n\n# Best-of redundancy for critical analysis\nclaw agent-orchestrator crew \\\n --task \"Audit this smart contract for vulnerabilities\" \\\n --agents 3 \\\n --converge best-of\n\n# Supervisor-managed code review\nclaw agent-orchestrator supervise \\\n --task \"Refactor authentication module\" \\\n --workers coder,reviewer,tester \\\n --strategy adaptive\n\n# Staged content pipeline\nclaw agent-orchestrator pipeline \\\n --stages research,draft,review,finalize \\\n --input \"topic: AI agent adoption trends\"\n\n# Expert council for decision\nclaw agent-orchestrator council \\\n --question \"Should we publish this blog post about unreleased features?\" \\\n --experts skeptic,ethicist,strategist \\\n --converge consensus \\\n --rounds 2\n\n# Auto-route mixed tasks\nclaw agent-orchestrator route \\\n --task \"Write Python function to analyze CSV data\" \\\n --specialists coder,researcher,writer,analyst\n\n# Force route to specific specialist\nclaw agent-orchestrator route \\\n --task \"Debug authentication error\" \\\n --force coder \\\n --confidence-threshold 0.9\n\n# Route and output as JSON for scripting\nclaw agent-orchestrator route \\\n --task $TASK \\\n --format json \\\n --specialists \"coder,data,analyst\"\n\nNegative Examples\n\nDON'T: Use crew for simple single-answer questions\n\n# WRONG: Wasteful for simple facts\nclaw agent-orchestrator crew --task \"What is 2+2?\" --agents 3\n\n# RIGHT: Use main session directly\nWhat is 2+2?\n\n\nDON'T: Use supervise when pipeline suffices\n\n# WRONG: Over-engineering fixed workflows\nclaw agent-orchestrator supervise --task \"Draft, edit, publish\"\n\n# RIGHT: Use pipeline for fixed sequences\nclaw agent-orchestrator pipeline --stages draft,edit,publish\n\n\nDON'T: Route when task type is obvious\n\n# WRONG: Unnecessary classification overhead\nclaw agent-orchestrator route --task \"Write Python code\"\n\n# RIGHT: Direct to appropriate specialist\nclaw agent-orchestrator crew --pattern code --task \"Write Python code\"\n\n\nDON'T: Use multi-agent for very small context tasks\n\n# WRONG: Coordination overhead exceeds value\nclaw agent-orchestrator crew --task \"Fix typo\" --agents 2\n\n# RIGHT: Single agent or direct edit\nedit file.py \"typo\" \"correct\"\n\nToken Cost Warning\n\nMulti-agent patterns use approximately 15x more tokens than single-agent interactions. Use only for high-value tasks where quality improvement justifies the cost. See Anthropic research: token usage explains 80% of performance variance in complex tasks.\n\nDependencies\nPython 3.8+\nOpenClaw sessions_spawn capability\nOpenClaw sessions_list capability\nOpenClaw sessions_history capability\nFiles\n__main__.py - CLI entry point\ncrew.py - Work Crew pattern implementation\nsupervise.py - Supervisor pattern (Phase 2)\ncouncil.py - Expert Council pattern (Phase 2)\npipeline.py - Pipeline pattern (Phase 2)\nroute.py - Auto-Routing pattern (Phase 2)\nutils.py - Shared utilities for session management\nStatus\nMVP: Work Crew pattern implemented\nPhase 2: 100% Complete\n Supervisor pattern implemented - dynamic task decomposition and worker delegation\n Pipeline pattern implemented - sequential staged processing with validation gates\n Council pattern implemented - multi-expert deliberation with convergence methods\n Route pattern implemented - intelligent task classification and specialist routing\nReferences\nAnthropic Multi-Agent Research System\nLangGraph Supervisor Pattern\nCrewAI Framework\nAutoGen Conversational Agents" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/variable190/agent-orchestrator-molter", "publisherUrl": "https://clawhub.ai/variable190/agent-orchestrator-molter", "owner": "variable190", "version": "1.0.5", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter", "downloadUrl": "https://openagent3.xyz/downloads/agent-orchestrator-molter", "agentUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-orchestrator-molter/agent.md" } }