agent-load-balancer

agent-load-balancer is a skill for Claude Code, Codex from ruvnet/ruflo. It costs 19 tokens per session (2,810 once invoked), scanned A, original, MIT.

A coordinator for distributing tasks among agents, including a work-stealing approach where an idle agent takes tasks from another agent's queue.

In plain words
What is it for?
Use it to schedule distributed tasks, allocate work dynamically, and rebalance queues when agents' workloads change.
Why use it?
It helps avoid uneven workloads in which some agents sit idle while others have too much work.

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-load-balancer
Any agent
npx skills add ruvnet/ruflo --skill agent-load-balancer
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-load-balancer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruvnet/ruflo/agent-load-balancer.svg)](https://agentmods.dev/skills/ruvnet/ruflo/agent-load-balancer)
Your own site
<a href="https://agentmods.dev/skills/ruvnet/ruflo/agent-load-balancer"><img src="https://agentmods.dev/badge/skills/ruvnet/ruflo/agent-load-balancer.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,810 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 $0.00019 $0.02810
Opus 5 $0.00010 $0.01405
Sonnet 5 $0.00004 $0.00562
Haiku 4.5 $0.00002 $0.00281

Measured 5d ago against content hash 23b2aa668ddf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-load-balancer 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 5d 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-load-balancer/SKILL.md · 436 lines

How it starts

The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: Load Balancing Coordinator type: agent category: optimization description: Dynamic task distribution, work-stealing algorithms and adaptive load balancing

Load Balancing Coordinator Agent

Agent Profile

  • Name: Load Balancing Coordinator
  • Type: Performance Optimization Agent
  • Specialization: Dynamic task distribution and resource allocation
  • Performance Focus: Work-stealing algorithms and adaptive load balancing

Core Capabilities

1. Work-Stealing Algorithms

// Advanced work-stealing implementation
const workStealingScheduler = {
  // Distributed queue system
  globalQueue: new PriorityQueue(),
  localQueues: new Map(), // agent-id -> local queue
  
  // Work-stealing algorithm
  async stealWork(requestingAgentId) {
    const victims = this.getVictimCandidates(requestingAgentId);
    
    for (const victim of victims) {
      const stolenTasks = await this.attemptSteal(victim, requestingAgentId);
      if (stolenTasks.length > 0) {
        return stolenTasks;
      }
    }
    
    // Fallback to global queue
    return await this.getFromGlobalQueue(requestingAgentId);
  },
  
  // Victim selection strategy
  getVictimCandidates(requestingAgent) {
    return Array.from(this.localQueues.entries())
      .filter(([agentId, queue]) => 
        agentId !== requestingAgent && 
        queue.size() > this.stealThreshold
      )
      .sort((a, b) => b[1].size() - a[1].size()) // Heaviest first
      .map(([agentId]) => agentId);
  }
};

2. Dynamic Load Balancing

// Real-time load balancing system
const loadBalancer = {
  // Agent capacity tracking
  agentCapacities: new Map(),
  currentLoads: new Map(),
  performanceMetrics: new Map(),
  
  // Dynamic load balancing
  async balanceLoad() {
    const agents = await this.getActiveAgents();
    const loadDistribution = this.calculateLoadDistribution(agents);
    
    // Identify overloaded and underloaded agents
    const { overloaded, underloaded } = this.categorizeAgents(loadDistribution);
    
    // Migrate tasks from overloaded to underloaded agents
    for (const overloadedAgent of overloaded) {
      const candidateTasks = await this.getMovableTasks(overloadedAgent.id);
      const targetAgent = this.selectTargetAgent(underloaded, candidateTasks);
      
      if (targetAgent) {
        await this.migrateTasks(candidateTasks, overloadedAgent.id, targetAgent.id);
      }
    }
  },
  
  // Weighted Fair Queuing implementation
  async scheduleWithWFQ(tasks) {
    const weights = await this.calculateAgentWeights();
    const virtualTimes = new Map();
    
    return tasks.sort((a, b) => {
      const aFinishTime = this.calculateFinishTime(a, weights, virtualTimes);
      const bFinishTime = this.calculateFinishTime(b, weights, virtualTimes);
      return aFinishTime - bFinishTime;
    });
  }
};

Read the full file on GitHub · 436 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. 5d ago First seen · 436 lines · 19 tokens per session scan A 23b2aa668ddf

Subscribe to this mod's changes

agent-load-balancer is a skill published in the GitHub repository ruvnet/ruflo (70,498 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,810 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

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

nw-jtbd-bdd-integration

Translating JTBD analysis to BDD scenarios - job story to Given-When-Then patterns, forces-based test discovery, job-map-based test discovery, and property-shaped criteria.

nWave-ai/nWave · 45 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