Worker Integration

by ruvnet60de638630abNo license74K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

Worker-Agent integration for intelligent task dispatch and performance tracking

Instructions onlyAI & Agents

AI-generated overview

Coordinates background workers with specialized agents, mapping triggers to agents and tracking performance.

What it does: This skill describes how background workers dispatch tasks to specialized agents based on trigger type, such as ultralearn, optimize, audit, benchmark, testgaps, document, deepdive, and refactor. It documents performance-based agent selection using quality score, success rate, latency, and execution count, plus memory key patterns for storing results. It also covers benchmark thresholds, a feedback loop for recording execution results, integration statistics, and configuration options.
When to use it: Use this skill when setting up or reasoning about worker-to-agent task dispatch and agent selection in an agentic-flow environment. It is also relevant when monitoring agent performance, benchmark compliance, or integration statistics.
Requirements: Requires the agentic-flow CLI and its worker-agent integration module, invoked via npx. Configuration is placed in .claude/settings.json. No scripts ship with the skill; it is instructions only.

Worker-Agent Integration Skill

Intelligent coordination between background workers and specialized agents.

Quick Start

bash

# View agent recommendations for a triggernpx agentic-flow workers agents ultralearnnpx agentic-flow workers agents optimize
# View performance metricsnpx agentic-flow workers metrics
# View integration statsnpx agentic-flow workers stats --integration

# View agent recommendations for a triggernpx agentic-flow workers agents ultralearnnpx agentic-flow workers agents optimize
# View performance metricsnpx agentic-flow workers metrics
# View integration statsnpx agentic-flow workers stats --integration

Agent Mappings

Workers automatically dispatch to optimal agents based on trigger type:

Trigger	Primary Agents	Fallback	Pipeline Phases
`ultralearn`	researcher, coder	planner	discovery → patterns → vectorization → summary
`optimize`	performance-analyzer, coder	researcher	static-analysis → performance → patterns
`audit`	security-analyst, tester	reviewer	security → secrets → vulnerability-scan
`benchmark`	performance-analyzer	coder, tester	performance → metrics → report
`testgaps`	tester	coder	discovery → coverage → gaps
`document`	documenter, researcher	coder	api-discovery → patterns → indexing
`deepdive`	researcher, security-analyst	coder	call-graph → deps → trace
`refactor`	coder, reviewer	researcher	complexity → smells → patterns

Performance-Based Selection

The system learns from execution history to improve agent selection:

typescript

// Agent selection considers:// 1. Quality score (0-1)// 2. Success rate// 3. Average latency// 4. Execution count
const { agent, confidence, reasoning } = selectBestAgent('optimize');// agent: "performance-analyzer"// confidence: 0.87// reasoning: "Selected based on 45 executions with 94.2% success"

// Agent selection considers:// 1. Quality score (0-1)// 2. Success rate// 3. Average latency// 4. Execution count
const { agent, confidence, reasoning } = selectBestAgent('optimize');// agent: "performance-analyzer"// confidence: 0.87// reasoning: "Selected based on 45 executions with 94.2% success"

Memory Key Patterns

Workers store results using consistent patterns:

{trigger}/{topic}/{phase}
Examples:- ultralearn/auth-module/analysis- optimize/database/performance- audit/payment/vulnerabilities- benchmark/api/metrics

{trigger}/{topic}/{phase}
Examples:- ultralearn/auth-module/analysis- optimize/database/performance- audit/payment/vulnerabilities- benchmark/api/metrics

Benchmark Thresholds

Agents are monitored against performance thresholds:

json

{  "researcher": {    "p95_latency": "<500ms",    "memory_mb": "<256MB"  },  "coder": {    "p95_latency": "<300ms",    "quality_score": ">0.85"  },  "security-analyst": {    "scan_coverage": ">95%",    "p95_latency": "<1000ms"  }}

{  "researcher": {    "p95_latency": "<500ms",    "memory_mb": "<256MB"  },  "coder": {    "p95_latency": "<300ms",    "quality_score": ">0.85"  },  "security-analyst": {    "scan_coverage": ">95%",    "p95_latency": "<1000ms"  }}

Feedback Loop

Workers provide feedback for continuous improvement:

typescript

import { workerAgentIntegration } from 'agentic-flow/workers/worker-agent-integration';
// Record execution feedbackworkerAgentIntegration.recordFeedback(  'optimize',           // trigger  'coder',              // agent  true,                 // success  245,                  // latency ms  0.92                  // quality score);
// Check complianceconst { compliant, violations } = workerAgentIntegration.checkBenchmarkCompliance('coder');

import { workerAgentIntegration } from 'agentic-flow/workers/worker-agent-integration';
// Record execution feedbackworkerAgentIntegration.recordFeedback(  'optimize',           // trigger  'coder',              // agent  true,                 // success  245,                  // latency ms  0.92                  // quality score);
// Check complianceconst { compliant, violations } = workerAgentIntegration.checkBenchmarkCompliance('coder');

Integration Statistics

bash

$ npx agentic-flow workers stats --integration
Worker-Agent Integration Stats══════════════════════════════Total Agents:       6Tracked Agents:     4Total Feedback:     156Avg Quality Score:  0.89
Model Cache Stats─────────────────Hits:     1,234Misses:   45Hit Rate: 96.5%

$ npx agentic-flow workers stats --integration
Worker-Agent Integration Stats══════════════════════════════Total Agents:       6Tracked Agents:     4Total Feedback:     156Avg Quality Score:  0.89
Model Cache Stats─────────────────Hits:     1,234Misses:   45Hit Rate: 96.5%

Configuration

Enable integration features in .claude/settings.json:

json

{  "workers": {    "enabled": true,    "parallel": true,    "memoryDepositEnabled": true,    "agentMappings": {      "ultralearn": ["researcher", "coder"],      "optimize": ["performance-analyzer", "coder"]    }  }}

{  "workers": {    "enabled": true,    "parallel": true,    "memoryDepositEnabled": true,    "agentMappings": {      "ultralearn": ["researcher", "coder"],      "optimize": ["performance-analyzer", "coder"]    }  }}

Source and attribution

Source:ruvnet/rufloin.claude/skills/worker-integrationat commit60de638

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Worker Integration

Worker-Agent Integration Skill

Quick Start

Agent Mappings

Performance-Based Selection

Memory Key Patterns

Benchmark Thresholds

Feedback Loop

Integration Statistics

Configuration

Source and attribution

More from ruvnet/ruflo

Cron Schedule

Autopilot Predict

Autopilot Loop

Worker Benchmarks

Swarm Advanced

Stream Chain

More in AI & Agents

Ppt Template Creator

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills