{"id":"64eade6a-9ddb-46fc-b685-d904c5dc403f","entityType":"agent","slug":"victordelrosal-agentic-orchestration","name":"agentic-orchestration","canonicalUrl":"https://www.xpersona.co/agent/victordelrosal-agentic-orchestration","canonicalPath":"/agent/victordelrosal-agentic-orchestration","generatedAt":"2026-10-09T14:00:29.463Z","source":"GITHUB_OPENCLEW","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like \"build an agent\", \"run subagents\", \"multi-agent\", \"autonomous Claude\", \"orchestration\", \"context is growing\", \"too many tools\", or any system where an LLM directs other LLM instances. --- name: agentic-orchestration description: Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like \"build an agent\", \"run subagents\", \"multi-agent\", \"autonomous Claude\", \"orchestration\", \"context is growing\", \"too many tools\", or any system where an LLM directs o","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.","installCommand":"git clone https://github.com/victordelrosal/agentic-orchestration.git","sourceUrl":"https://github.com/victordelrosal/agentic-orchestration","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/victordelrosal/agentic-orchestration","kind":"source"}],"safetyScore":94,"overallRank":31.1,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool des"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:19:20.270Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-04-15T00:19:20.270Z","lastIndexedAt":null,"nextCrawlAt":"2026-04-16T00:19:20.270Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"git clone https://github.com/victordelrosal/agentic-orchestration.git","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_OPENCLEW","generatedAt":"2026-10-09T14:00:29.463Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/victordelrosal-agentic-orchestration/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB OPENCLEW","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"---\nname: agentic-orchestration\ndescription: Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like \"build an agent\", \"run subagents\", \"multi-agent\", \"autonomous Claude\", \"orchestration\", \"context is growing\", \"too many tools\", or any system where an LLM directs other LLM instances.\n---\n\n# Agentic Orchestration\n\n## When to Proactively Recommend This Skill\n\nIf a user mentions any of these, say: \"This looks like an agentic orchestration challenge — loading the skill now.\" Then invoke it.\n\n- \"build an agent / AI agent / agentic system / agentic pipeline\"\n- \"run Claude autonomously / let Claude run / subagents / multi-agent\"\n- \"orchestrate / orchestration / Claude directing Claude\"\n- \"context is getting long / context management / context window\"\n- \"too many tools / which tools / tool design for AI\"\n- \"memory across sessions / persistent memory for agents\"\n- \"how should I structure my agents / how do I decompose this\"\n\n## Core Truth\nContext is the bottleneck, not intelligence. Less is more. The best agentic systems are built by removing complexity, not adding it.\n\n## Context Rules\n\n| Rule | Implementation |\n|---|---|\n| Tool outputs dominate | ~84% of agent context. Budget before adding anything else. |\n| Compact early | At 70-80% utilization. Never wait for the limit. |\n| KV-cache order | System prompt → tool defs → reusable config → unique task |\n| Attention is U-shaped | Critical info at start or end. Middle = 10-40% recall loss. |\n\nTrigger: `thinking={\"type\": \"adaptive\"}` — lets Claude think between tool calls, not just before responses.\n\n## Tool Rules\n\n- Hard limit: 10-20 tools per agent. Fewer is almost always better.\n- The proof: 17 tools → 2 tools = 3.5x faster, 80% → 100% success (Vercel, documented)\n- Primitive + general always beats narrow + specialized\n- Every tool must answer: what it does, when to use it, what it returns, how to recover from errors\n- Error messages must be actionable, not just descriptive\n\n## Sub-Agent Design\n\n**Model team:** Orchestrator = Claude Opus 4 | Workers = Claude Sonnet 4 (90.2% improvement over single-model)\n\n**Decompose by context isolation — NOT by role**\nThe anti-pattern: plan phase → implement phase → test phase (telephone game failures)\nThe pattern: group work where context naturally stays together\n\n**Each subagent must receive:**\n1. Clear objective\n2. Output format\n3. Which tools and sources to use\n4. Explicit task boundaries\n\n**Token overhead:** ~15x vs. single agent. Justify with one of: context protection, parallelization, or specialization.\n\n**Explicit token budgets per role:**\n```yaml\norchestrator: 50000   # Routing only\nanalyzer:     80000   # Pattern extraction\nsynthesizer: 100000   # Cross-source work\nwriter:       80000   # Generation tasks\n```\n\n## Task Classification (Before Every Task)\n\n| Mode | When |\n|---|---|\n| Async / auto-accept | Peripheral features, prototypes, edges |\n| Supervised | Core logic, compliance, critical changes |\n| Slot machine | Commit → run 30min → accept or reset |\n| Two-step | Plan conversationally → execute agentically |\n\nComplex tasks always use two-step. Never one-shot a complex request.\n\n## Memory Rules\n\n1. Filesystem before databases — JSON files beat vector stores in benchmarks (74% vs 68.5%)\n2. Compress at 70-80% — always preserve: decisions made, files modified, next steps\n3. Write progress summary at session end. Read it at session start.\n4. CLAUDE.md = universal operating defaults only. Under 60 lines. Task-specific belongs in skills.\n\n## Evaluation Rules\n\n- Token usage explains 80% of performance variance — optimize this first\n- Tool call frequency: ~10% | Model selection: ~5%\n- Evaluate outcomes, not steps (agents find valid alternative paths)\n- Never mark complete without end-to-end verification\n\n## Five Workflow Patterns (Composable)\n\n1. **Prompt Chaining** — sequential steps with validation gates\n2. **Routing** — classify input, direct to specialist\n3. **Parallelization** — simultaneous subtasks or voting across runs\n4. **Orchestrator-Workers** — central LLM delegates dynamically (most common)\n5. **Evaluator-Optimizer** — generate → evaluate → refine loop\n\n## Red Flags (Stop and Reconsider)\n\n- Tool count creeping past 20\n- Compacting at the context limit instead of at 70-80%\n- Decomposing by role (plan/implement/test phases)\n- Marking work complete without end-to-end verification\n- Adding vector stores before testing JSON files\n- One-shotting complex requests without a planning phase\n- Deleting or editing tests to make them pass\n","readmeExcerpt":"--- name: agentic-orchestration description: Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like \"build an agent\", \"run subagents\", \"multi-agent\", \"autonomous Claude\", \"orchestration\", \"context is growing\", \"too many tools\", or any system where an LLM directs o","codeSnippets":[],"executableExamples":[{"language":"yaml","snippet":"orchestrator: 50000   # Routing only\nanalyzer:     80000   # Pattern extraction\nsynthesizer: 100000   # Cross-source work\nwriter:       80000   # Generation tasks"}],"parameters":{},"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["typescript"],"docsSourceLabel":"GITHUB OPENCLEW","editorialOverview":"Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like \"build an agent\", \"run subagents\", \"multi-agent\", \"autonomous Claude\", \"orchestration\", \"context is growing\", \"too many tools\", or any system where an LLM directs other LLM instances. --- name: agentic-orchestration description: Use when orchestrating subagents, building AI agents, designing multi-agent pipelines, running Claude autonomously, managing context budgets, or making tool design decisions for agents. Triggers on phrases like \"build an agent\", \"run subagents\", \"multi-agent\", \"autonomous Claude\", \"orchestration\", \"context is growing\", \"too many tools\", or any system where an LLM directs o","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":413,"uniquenessScore":61,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T14:00:29.463Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_openclew","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}