V3 Performance Optimization

V3 Performance Optimization is a skill for Claude Code, Codex from ruvnet/RuView. It costs 53 tokens per session (2,435 once invoked), scanned A, original, MIT.

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ruvnet/ruview/v3-performance-optimization
Any agent
npx skills add ruvnet/RuView --skill v3-performance-optimization
Clone the repo
git clone --depth 1 https://github.com/ruvnet/RuView

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for V3 Performance Optimization

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruview/v3-performance-optimization.svg)](https://agentmods.dev/skills/ruvnet/ruview/v3-performance-optimization)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruview/v3-performance-optimization"><img src="https://agentmods.dev/badge/skills/ruvnet/ruview/v3-performance-optimization.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.02435
Opus 5 $0.00026 $0.01218
Sonnet 5 $0.00011 $0.00487
Haiku 4.5 $0.00005 $0.00244

Measured today against content hash 25858e4c4325, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

V3 Performance Optimization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/v3-performance-optimization/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

V3 Performance Optimization

What This Skill Does

Validates and optimizes claude-flow v3 to achieve industry-leading performance through Flash Attention, AgentDB HNSW indexing, and comprehensive system optimization with continuous benchmarking.

Quick Start

# Initialize performance optimization
Task("Performance baseline", "Establish v2 performance benchmarks", "v3-performance-engineer")

# Target validation (parallel)
Task("Flash Attention", "Validate 2.49x-7.47x speedup target", "v3-performance-engineer")
Task("Search optimization", "Validate 150x-12,500x search improvement", "v3-performance-engineer")
Task("Memory optimization", "Achieve 50-75% memory reduction", "v3-performance-engineer")

Performance Target Matrix

Flash Attention Revolution

┌─────────────────────────────────────────┐
│           FLASH ATTENTION               │
├─────────────────────────────────────────┤
│  Baseline: Standard attention           │
│  Target:   2.49x - 7.47x speedup       │
│  Memory:   50-75% reduction             │
│  Latency:  Sub-millisecond processing   │
└─────────────────────────────────────────┘

Search Performance Revolution

┌─────────────────────────────────────────┐
│            SEARCH OPTIMIZATION         │
├─────────────────────────────────────────┤
│  Current:  O(n) linear search           │
│  Target:   150x - 12,500x improvement   │
│  Method:   HNSW indexing                │
│  Latency:  <100ms for 1M+ entries       │
└─────────────────────────────────────────┘

Comprehensive Benchmark Suite

Startup Performance

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

    await this.initializeCLI();
    await this.initializeMCPServer();
    await this.spawnTestAgent();

    const totalTime = performance.now() - startTime;

    return {
      total: totalTime,
      target: 500, // ms
      achieved: totalTime < 500
    };
  }
}

Read the full file on GitHub · 390 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 390 lines · 53 tokens per session scan A 25858e4c4325

Subscribe to this mod's changes

V3 Performance Optimization is a skill published in the GitHub repository ruvnet/RuView (92,406 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 2,435 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.