agent-benchmark-suite

agent-benchmark-suite is a skill for Claude Code, Codex from ruvnet/ruflo. It costs 18 tokens per session (4,197 once invoked), scanned A, original, MIT.

A performance testing skill that measures throughput, response time, scaling, resource use, coordination, load balancing, topology, and fault tolerance.

In plain words
What is it for?
Use it to run standard or custom benchmarks, detect performance regressions, and validate system behavior under different loads.
Why use it?
It helps show whether a system is getting slower or less reliable after a change by comparing measured results over time.

Skill for Claude CodeCodex

Part of the claude-flow plugin — 134 skills, 52 commands, 11 agents, 4 hooks shipped together

About the project

Ruflo is an execution and coordination layer for Claude Code and Codex that equips AI coding agents with tools, memory, control loops, sandboxes, and collaboration mechanisms. Developers use it to organize specialized agents into swarms, coordinate workflows, retain knowledge across sessions, and communicate across machines. The catalogue entries are Ruflo’s skills, commands, agents, hooks, and plugin components.

ruvnet/ruflo · 70,498 stars · on GitHub

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/ruflo/agent-benchmark-suite
Any agent
npx skills add ruvnet/ruflo --skill agent-benchmark-suite
Clone the repo
git clone --depth 1 https://github.com/ruvnet/ruflo

Made for: Claude Code, Codex.

Or install claude-flow, the plugin that ships this one along with the rest of its 134 skills, 52 commands, 11 agents, 4 hooks.

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 agent-benchmark-suite

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruflo/agent-benchmark-suite.svg)](https://agentmods.dev/skills/ruvnet/ruflo/agent-benchmark-suite)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruflo/agent-benchmark-suite"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/agent-benchmark-suite.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,197 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00018 $0.04197
Opus 5 $0.00009 $0.02099
Sonnet 5 $0.00004 $0.00839
Haiku 4.5 $0.00002 $0.00420

Measured 6d ago against content hash 41c15d830659, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-benchmark-suite 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 6d ago.

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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

.agents/skills/agent-benchmark-suite/SKILL.md · 670 lines

How it starts

The opening of the file, as written. The whole thing — 670 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: Benchmark Suite type: agent category: optimization description: Comprehensive performance benchmarking, regression detection and performance validation

Benchmark Suite Agent

Agent Profile

  • Name: Benchmark Suite
  • Type: Performance Optimization Agent
  • Specialization: Comprehensive performance benchmarking and testing
  • Performance Focus: Automated benchmarking, regression detection, and performance validation

Core Capabilities

1. Comprehensive Benchmarking Framework

// Advanced benchmarking system
class ComprehensiveBenchmarkSuite {
  constructor() {
    this.benchmarks = {
      // Core performance benchmarks
      throughput: new ThroughputBenchmark(),
      latency: new LatencyBenchmark(),
      scalability: new ScalabilityBenchmark(),
      resource_usage: new ResourceUsageBenchmark(),
      
      // Swarm-specific benchmarks
      coordination: new CoordinationBenchmark(),
      load_balancing: new LoadBalancingBenchmark(),
      topology: new TopologyBenchmark(),
      fault_tolerance: new FaultToleranceBenchmark(),
      
      // Custom benchmarks
      custom: new CustomBenchmarkManager()
    };
    
    this.reporter = new BenchmarkReporter();
    this.comparator = new PerformanceComparator();
    this.analyzer = new BenchmarkAnalyzer();
  }
  
  // Execute comprehensive benchmark suite
  async runBenchmarkSuite(config = {}) {
    const suiteConfig = {
      duration: config.duration || 300000, // 5 minutes default
      iterations: config.iterations || 10,
      warmupTime: config.warmupTime || 30000, // 30 seconds
      cooldownTime: config.cooldownTime || 10000, // 10 seconds
      parallel: config.parallel || false,
      baseline: config.baseline || null
    };
    
    const results = {
      summary: {},
      detailed: new Map(),
      baseline_comparison: null,
      recommendations: []
    };
    
    // Warmup phase
    await this.warmup(suiteConfig.warmupTime);
    
    // Execute benchmarks
    if (suiteConfig.parallel) {
      results.detailed = await this.runBenchmarksParallel(suiteConfig);
    } else {
      results.detailed = await this.runBenchmarksSequential(suiteConfig);
    }
    
    // Generate summary
    results.summary = this.generateSummary(results.detailed);
    
    // Compare with baseline if provided
    if (suiteConfig.baseline) {
      results.baseline_comparison = await this.compareWithBaseline(
        results.detailed, 
        suiteConfig.baseline
      );
    }
    
    // Generate recommendations
    results.recommendations = await this.generateRecommendations(results);
    
    // Cooldown phase
    await this.cooldown(suiteConfig.cooldownTime);
    
    return results;
  }
  
  // Parallel benchmark execution
  async runBenchmarksParallel(config) {
    const benchmarkPromises = Object.entries(this.benchmarks).map(
      async ([name, benchmark]) => {
        const result = await this.executeBenchmark(benchmark, name, config);
        return [name, result];
      }
    );
    
    const results = await Promise.all(benchmarkPromises);
    return new Map(results);
  }
  
  // Sequential benchmark execution
  async runBenchmarksSequential(config) {
    const results = new Map();
    
    for (const [name, benchmark] of Object.entries(this.benchmarks)) {
      const result = await this.executeBenchmark(benchmark, name, config);
      results.set(name, result);
      
      // Brief pause between benchmarks
      await this.sleep(1000);
    }
    
    return results;
  }
}

Read the full file on GitHub · 670 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. 6d ago First seen · 670 lines · 18 tokens per session scan A 41c15d830659

Subscribe to this mod's changes

agent-benchmark-suite is a skill published in the GitHub repository ruvnet/ruflo (70,498 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 4,197 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

external-memory-plugin

Develop, adapt, review, test, and troubleshoot Nexent external memory provider plugins, including plugin.yaml manifests, searchable and ingestible provider protocols, error mapping, network-isolated unit tests, deployment configuration, and Mem0-based examples. Use when adding a new external memory vendor, changing an…

ModelEngine-Group/nexent · 85 tokens

nw-design

Designs system architecture with C4 diagrams and technology selection. Routes to the right architect based on design scope (system, domain, application, or full stack). Two interaction modes: guide (collaborative Q&A) or propose (architect presents options with trade-offs).

nWave-ai/nWave · 57 tokens

compare-harnesses

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

ruvnet/metaharness · 66 tokens

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

repo-genome

7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.

ruvnet/metaharness · 73 tokens

score-harness

5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.

ruvnet/metaharness · 0 tokens