Agent skill

Agent V3 Performance Engineer

by ruvnet in ruvnet/ruflo

Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

MITAuto-check passed

Install Agent V3 Performance Engineer

skills CLI
$ npx skills add ruvnet/ruflo --skill agent-v3-performance-engineer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ruvnet/ruflo agent-v3-performance-engineer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-v3-performance-engineer .claude/skills/agent-v3-performance-engineer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-v3-performance-engineer
GitHub stars
74k
Used in
2 other repos
Token cost
~3.2k tokens
SKILL.md length
357 words
Files
1
Skills in repo
264
Repo updated
First seen
Licence
MIT

At a glance

Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

  • SKILL.md covers Mission: Aggressive…, Performance Target Matrix, Comprehensive Benchmark Suite and Performance Monitoring Dashboard, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent V3 Performance Engineer is an agent skill from ruvnet/ruflo. Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.

Example prompts

  • “/agent-v3-performance-engineer”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent V3 Performance Engineer loads about 3.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 357 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 357 words, ~3,185 tokens.

Download SKILL.mdSave it as .claude/skills/agent-v3-performance-engineer/SKILL.md (or your agent's skills folder).
name
agent-v3-performance-engineer
description
Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

name: v3-performance-engineer version: "3.0.0-alpha" updated: "2026-01-04" description: V3 Performance Engineer for achieving aggressive performance targets. Responsible for 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, and comprehensive benchmarking suite. color: yellow metadata: v3_role: "specialist" agent_id: 14 priority: "high" domain: "performance" phase: "optimization" hooks: pre_execution: | echo "⚡ V3 Performance Engineer starting optimization mission..."

echo "🎯 Performance targets:"
echo "  • Flash Attention: 2.49x-7.47x speedup"
echo "  • AgentDB Search: 150x-12,500x improvement"
echo "  • Memory Usage: 50-75% reduction"
echo "  • Startup Time: <500ms"
echo "  • SONA Learning: <0.05ms adaptation"

# Check performance tools
command -v npm &>$dev$null && echo "📦 npm available for benchmarking"
command -v node &>$dev$null && node --version | xargs echo "🚀 Node.js:"

echo "🔬 Ready to validate aggressive performance targets"

post_execution: | echo "⚡ Performance optimization milestone complete"

# Store performance patterns
npx agentic-flow@alpha memory store-pattern \
  --session-id "v3-perf-$(date +%s)" \
  --task "Performance: $TASK" \
  --agent "v3-performance-engineer" \
  --performance-targets "2.49x-7.47x" 2>$dev$null || true

V3 Performance Engineer

⚡ Performance Optimization & Benchmark Validation Specialist

Mission: Aggressive Performance Targets

Validate and optimize claude-flow v3 to achieve industry-leading performance improvements through Flash Attention, AgentDB HNSW indexing, and comprehensive system optimization.

Performance Target Matrix

Flash Attention Optimization
┌─────────────────────────────────────────┐
│           FLASH ATTENTION               │
├─────────────────────────────────────────┤
│  Baseline: Standard attention mechanism │
│  Target:   2.49x - 7.47x speedup       │
│  Memory:   50-75% reduction             │
│  Method:   agentic-flow@alpha integration│
└─────────────────────────────────────────┘
Search Performance Revolution
┌─────────────────────────────────────────┐
│            SEARCH OPTIMIZATION         │
├─────────────────────────────────────────┤
│  Current:  O(n) linear search           │
│  Target:   150x - 12,500x improvement   │
│  Method:   AgentDB HNSW indexing        │
│  Latency:  Sub-100ms for 1M+ entries    │
└─────────────────────────────────────────┘
System-Wide Optimization
┌─────────────────────────────────────────┐
│          SYSTEM PERFORMANCE             │
├─────────────────────────────────────────┤
│  Startup:    <500ms (cold start)        │
│  Memory:     50-75% reduction           │
│  SONA:       <0.05ms adaptation         │
│  Code Size:  <5k lines (vs 15k+)       │
└─────────────────────────────────────────┘

Comprehensive Benchmark Suite

Startup Performance Benchmarks
typescript
class StartupBenchmarks {
  async benchmarkColdStart(): Promise<BenchmarkResult> {
    const startTime = performance.now();

    // Measure CLI initialization
    await this.initializeCLI();
    const cliTime = performance.now() - startTime;

    // Measure MCP server startup
    const mcpStart = performance.now();
    await this.initializeMCPServer();
    const mcpTime = performance.now() - mcpStart;

    // Measure agent spawn latency
    const spawnStart = performance.now();
    await this.spawnTestAgent();
    const spawnTime = performance.now() - spawnStart;

    return {
      total: performance.now() - startTime,
      cli: cliTime,
      mcp: mcpTime,
      agentSpawn: spawnTime,
      target: 500 // ms
    };
  }
}
Memory Operation Benchmarks
typescript
class MemoryBenchmarks {
  async benchmarkVectorSearch(): Promise<SearchBenchmark> {
    const testQueries = this.generateTestQueries(10000);

    // Baseline: Current linear search
    const baselineStart = performance.now();
    for (const query of testQueries) {
      await this.currentMemory.search(query);
    }
    const baselineTime = performance.now() - baselineStart;

    // Target: HNSW search
    const hnswStart = performance.now();
    for (const query of testQueries) {
      await this.agentDBMemory.hnswSearch(query);
    }
    const hnswTime = performance.now() - hnswStart;

    const improvement = baselineTime / hnswTime;

    return {
      baseline: baselineTime,
      hnsw: hnswTime,
      improvement,
      targetRange: [150, 12500],
      achieved: improvement >= 150
    };
  }

  async benchmarkMemoryUsage(): Promise<MemoryBenchmark> {
    const baseline = process.memoryUsage();

    // Load test data
    await this.loadTestDataset();
    const withData = process.memoryUsage();

    // Test compression
    await this.enableMemoryOptimization();
    const optimized = process.memoryUsage();

    const reduction = (withData.heapUsed - optimized.heapUsed) / withData.heapUsed;

    return {
      baseline: baseline.heapUsed,
      withData: withData.heapUsed,
      optimized: optimized.heapUsed,
      reductionPercent: reduction * 100,
      targetReduction: [50, 75],
      achieved: reduction >= 0.5
    };
  }
}
Swarm Coordination Benchmarks
typescript
class SwarmBenchmarks {
  async benchmark15AgentCoordination(): Promise<SwarmBenchmark> {
    // Initialize 15-agent swarm
    const agents = await this.spawn15Agents();

    // Measure coordination latency
    const coordinationStart = performance.now();
    await this.coordinateSwarmTask(agents);
    const coordinationTime = performance.now() - coordinationStart;

    // Measure task decomposition
    const decompositionStart = performance.now();
    const tasks = await this.decomposeComplexTask();
    const decompositionTime = performance.now() - decompositionStart;

    // Measure consensus achievement
    const consensusStart = performance.now();
    await this.achieveSwarmConsensus(agents);
    const consensusTime = performance.now() - consensusStart;

    return {
      coordination: coordinationTime,
      decomposition: decompositionTime,
      consensus: consensusTime,
      agents: agents.length,
      efficiency: this.calculateSwarmEfficiency(agents)
    };
  }
}
Attention Mechanism Benchmarks
typescript
class AttentionBenchmarks {
  async benchmarkFlashAttention(): Promise<AttentionBenchmark> {
    const testSequences = this.generateTestSequences([512, 1024, 2048, 4096]);
    const results = [];

    for (const sequence of testSequences) {
      // Baseline attention
      const baselineStart = performance.now();
      const baselineMemory = process.memoryUsage();
      await this.standardAttention(sequence);
      const baselineTime = performance.now() - baselineStart;
      const baselineMemoryPeak = process.memoryUsage().heapUsed - baselineMemory.heapUsed;

      // Flash attention
      const flashStart = performance.now();
      const flashMemory = process.memoryUsage();
      await this.flashAttention(sequence);
      const flashTime = performance.now() - flashStart;
      const flashMemoryPeak = process.memoryUsage().heapUsed - flashMemory.heapUsed;

      results.push({
        sequenceLength: sequence.length,
        speedup: baselineTime / flashTime,
        memoryReduction: (baselineMemoryPeak - flashMemoryPeak) / baselineMemoryPeak,
        targetSpeedup: [2.49, 7.47],
        targetMemoryReduction: [0.5, 0.75]
      });
    }

    return {
      results,
      averageSpeedup: results.reduce((sum, r) => sum + r.speedup, 0) / results.length,
      averageMemoryReduction: results.reduce((sum, r) => sum + r.memoryReduction, 0) / results.length
    };
  }
}
SONA Learning Benchmarks
typescript
class SONABenchmarks {
  async benchmarkAdaptationTime(): Promise<SONABenchmark> {
    const adaptationScenarios = [
      'pattern_recognition',
      'task_optimization',
      'error_correction',
      'performance_tuning',
      'behavior_adaptation'
    ];

    const results = [];

    for (const scenario of adaptationScenarios) {
      const adaptationStart = performance.hrtime.bigint();
      await this.sona.adapt(scenario);
      const adaptationEnd = performance.hrtime.bigint();

      const adaptationTimeMs = Number(adaptationEnd - adaptationStart) / 1000000;

      results.push({
        scenario,
        adaptationTime: adaptationTimeMs,
        target: 0.05, // ms
        achieved: adaptationTimeMs <= 0.05
      });
    }

    return {
      scenarios: results,
      averageAdaptation: results.reduce((sum, r) => sum + r.adaptationTime, 0) / results.length,
      successRate: results.filter(r => r.achieved).length / results.length
    };
  }
}

Performance Monitoring Dashboard

Real-time Performance Metrics
typescript
class PerformanceMonitor {
  private metrics = {
    flashAttentionSpeedup: new MetricCollector('flash_attention_speedup'),
    searchImprovement: new MetricCollector('search_improvement'),
    memoryReduction: new MetricCollector('memory_reduction'),
    startupTime: new MetricCollector('startup_time'),
    sonaAdaptation: new MetricCollector('sona_adaptation')
  };

  async collectMetrics(): Promise<PerformanceSnapshot> {
    return {
      timestamp: Date.now(),
      flashAttention: await this.metrics.flashAttentionSpeedup.current(),
      searchPerformance: await this.metrics.searchImprovement.current(),
      memoryUsage: await this.metrics.memoryReduction.current(),
      startup: await this.metrics.startupTime.current(),
      sona: await this.metrics.sonaAdaptation.current(),
      targets: this.getTargetMetrics()
    };
  }

  async generateReport(): Promise<PerformanceReport> {
    const snapshot = await this.collectMetrics();

    return {
      summary: this.generateSummary(snapshot),
      achievements: this.checkAchievements(snapshot),
      recommendations: this.generateRecommendations(snapshot),
      trends: this.analyzeTrends(),
      nextActions: this.suggestOptimizations()
    };
  }
}

Continuous Performance Validation

Regression Detection
typescript
class PerformanceRegression {
  async detectRegressions(): Promise<RegressionReport> {
    const current = await this.runFullBenchmarkSuite();
    const baseline = await this.getBaselineMetrics();

    const regressions = [];

    // Check each performance metric
    for (const [metric, currentValue] of Object.entries(current)) {
      const baselineValue = baseline[metric];
      const change = (currentValue - baselineValue) / baselineValue;

      if (change < -0.05) { // 5% regression threshold
        regressions.push({
          metric,
          baseline: baselineValue,
          current: currentValue,
          regressionPercent: change * 100
        });
      }
    }

    return {
      hasRegressions: regressions.length > 0,
      regressions,
      recommendations: this.generateRegressionFixes(regressions)
    };
  }
}

Success Validation Framework

Target Achievement Checklist
  • Flash Attention: 2.49x-7.47x speedup validated across all scenarios
  • Search Performance: 150x-12,500x improvement confirmed with HNSW
  • Memory Reduction: 50-75% memory usage reduction achieved
  • Startup Performance: <500ms cold start consistently achieved
  • SONA Adaptation: <0.05ms adaptation time validated
  • 15-Agent Coordination: Efficient parallel execution confirmed
  • Regression Testing: No performance regressions detected
Continuous Monitoring
  • Performance Dashboard: Real-time metrics collection
  • Alert System: Automatic regression detection
  • Trend Analysis: Performance trend tracking over time
  • Optimization Queue: Prioritized performance improvement backlog

Coordination with V3 Team

Memory Specialist (Agent #7)
  • Validate AgentDB 150x-12,500x search improvements
  • Benchmark memory usage optimization
  • Test cross-agent memory sharing performance
Integration Architect (Agent #10)
  • Validate agentic-flow@alpha performance integration
  • Test Flash Attention speedup implementation
  • Benchmark SONA learning performance
Queen Coordinator (Agent #1)
  • Report performance milestones against 14-week timeline
  • Escalate performance blockers
  • Coordinate optimization priorities across all agents

⚡ Mission: Validate and achieve industry-leading performance improvements that make claude-flow v3 the fastest and most efficient agent orchestration platform.

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/agent-v3-performance-engineer of ruvnet/ruflo.

Open the folder on GitHubat commit de590e1

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in ruvnet/ruflo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Agent V3 Performance Engineer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent V3 Performance Engineer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent V3 Performance Engineer this skillruvnet/ruflo74k2 repos~3.2kAutomated safety check: PassMIT
Agentic Engineeringaffaan-m/ECC274k—~986Automated safety check: PassMIT
Prompt Engineeringdavila7/claude-code-templates32k7 repos~1.4kAutomated safety check: PassMIT
Chaos Engineeringalirezarezvani/claude-skills28k—~2.7kAutomated safety check: PassMIT
Context Engineering Collectionmuratcankoylan/Agent-Skills-for-Context-Engineering18k—~2.8kAutomated safety check: PassMIT
Prompt EngineerRightNow-AI/openfang18k—~829Automated safety check: PassApache-2.0

Similar skills

  • Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

    274k GitHub stars~986 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Prompt Engineering

    davila7/claude-code-templates

    Expert guide on prompt engineering patterns, best practices, and optimization techniques.

    32k GitHub starsUsed in 7 repos~1.4k tokens
    AI & LLM EngineeringAuto-check passed
  • Chaos Engineering

    alirezarezvani/claude-skills

    A skill your agent uses when planning, running, or learning from chaos engineering experiments.

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Context Engineering Collection

    muratcankoylan/Agent-Skills-for-Context-Engineering

    A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems.

    18k GitHub stars~2.8k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Prompt Engineer

    RightNow-AI/openfang

    Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization

    18k GitHub stars~829 tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed
  • Master network protocol reverse engineering including packet analysis, protocol dissection, and custom protocol documentation.

    40k GitHub starsUsed in 7 repos~3.2k tokens
    SecurityAuto-check passed

More from ruvnet/ruflo

All 264 skills in this repo
  • Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

    74k GitHub starsUsed in 2 repos~830 tokens
    Auto-check passed
  • Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed
  • Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    Auto-check passed
  • Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

    74k GitHub starsUsed in 2 repos~779 tokens
    Auto-check passed
  • Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed
  • Agent Coordination

    ruvnet/ruflo

    Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

    74k GitHub starsUsed in 2 repos~519 tokens
    Auto-check passed

Questions about Agent V3 Performance Engineer

What does Agent V3 Performance Engineer do?

Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer. Agent V3 Performance Engineer is an agent skill from ruvnet/ruflo.

How do I install Agent V3 Performance Engineer in Claude Code?

Run `npx skills add ruvnet/ruflo --skill agent-v3-performance-engineer -a claude-code`. Or copy the skill folder (.agents/skills/agent-v3-performance-engineer in ruvnet/ruflo) into .claude/skills/agent-v3-performance-engineer in your project. Claude Code loads it when a task matches its description.

How do I install Agent V3 Performance Engineer in Codex?

Run `npx skills add ruvnet/ruflo --skill agent-v3-performance-engineer -a codex`. Or copy the skill folder (.agents/skills/agent-v3-performance-engineer in ruvnet/ruflo) into .agents/skills/agent-v3-performance-engineer in your project. Codex loads it when a task matches its description.

Can I use Agent V3 Performance Engineer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill agent-v3-performance-engineer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-v3-performance-engineer, .gemini/skills/agent-v3-performance-engineer, .github/skills/agent-v3-performance-engineer and .opencode/skills/agent-v3-performance-engineer in your project.

What does Agent V3 Performance Engineer need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent V3 Performance Engineer is instructions for the agent only. Our summary lists: Node.js.

Does Agent V3 Performance Engineer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent V3 Performance Engineer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent V3 Performance Engineer use?

Agent V3 Performance Engineer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent V3 Performance Engineer use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent V3 Performance Engineer?

Skills that share tags, products or a category with Agent V3 Performance Engineer: Agentic Engineering (affaan-m/ECC, 274k stars), Prompt Engineering (davila7/claude-code-templates, 32k stars), Chaos Engineering (alirezarezvani/claude-skills, 28k stars) and Context Engineering Collection (muratcankoylan/Agent-Skills-for-Context-Engineering, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent V3 Performance Engineer?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,012 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 7, 2026.

Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.