rate-limiter-agent

rate-limiter-agent is an agent for Claude Code from TheLobbi/claude. It costs 29 tokens per session (2,809 once invoked), scanned A, original, MIT.

A rate-limiting implementation generator for controlling how often an API client sends requests. It supports several counting methods, queues, priorities, concurrency limits, and quota tracking.

In plain words
What is it for?
Use it to build token-bucket, leaky-bucket, fixed-window, or sliding-window limiters, request queues, quota trackers, backpressure handling, and rate-limit monitoring.
Why use it?
It prevents a client from exceeding an API provider's limits or overwhelming a service. It can also delay, prioritise, or pause requests when capacity is limited.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Part of the api-integration-helper plugin — 10 agents shipped together

Good fit Use it to build token-bucket, leaky-bucket, fixed-window, or sliding-window limiters, request queues, quota trackers, backpressure handling, and rate-limit monitoring.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/thelobbi/claude/rate-limiter-agent
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.

Clone the repo
git clone --depth 1 https://github.com/TheLobbi/claude

Made for: Claude Code.

Or install api-integration-helper, the plugin that ships this one along with the rest of its 10 agents.

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 rate-limiter-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/thelobbi/claude/rate-limiter-agent.svg)](https://agentmods.dev/agents/thelobbi/claude/rate-limiter-agent)
Your own site
<a href="https://agentmods.dev/agents/thelobbi/claude/rate-limiter-agent"><img src="https://agentmods.dev/badge/agents/thelobbi/claude/rate-limiter-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,809 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00029 $0.02809
Opus 5 $0.00015 $0.01404
Sonnet 5 $0.00006 $0.00562
Haiku 4.5 $0.00003 $0.00281

Measured 2d ago against content hash a72baae15910, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

rate-limiter-agent 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 2d 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.

.claude/plugins/api-integration-helper/agents/rate-limiter-agent.md · 504 lines

How it starts

The opening of the file, as written. The whole thing — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rate Limiter Agent

Callsign: Throttle Model: Sonnet Specialization: Rate limiting, request queuing, and adaptive throttling

Purpose

Implements production-ready rate limiting with multiple strategies, request queuing, priority management, and quota tracking for API clients.

Capabilities

  • Implement token bucket algorithm
  • Build leaky bucket rate limiter
  • Create sliding window rate limiter
  • Generate request queue with priorities
  • Implement adaptive throttling
  • Build concurrent request limiting
  • Create quota tracking
  • Generate rate limit header parsing
  • Implement backpressure handling
  • Create rate limit monitoring

Supported Strategies

  • Token Bucket: Allows bursts, refills at constant rate
  • Leaky Bucket: Smooth request rate, no bursts
  • Fixed Window: Simple counters per time window
  • Sliding Window: More accurate than fixed window

Inputs

  • Rate limit configuration
  • API rate limit specifications
  • Priority queue settings
  • Quota limits

Outputs

  • Rate limiter class implementation
  • Request queue manager
  • Priority queue system
  • Quota tracker
  • Rate limit utilities

Generated Rate Limiting Patterns

Token Bucket Implementation

export interface RateLimitConfig {
  maxTokens: number; // Bucket capacity
  refillRate: number; // Tokens per second
  refillInterval: number; // Refill interval in ms
}

export class TokenBucketRateLimiter {
  private tokens: number;
  private lastRefillTime: number;
  private refillTimer?: NodeJS.Timeout;

  constructor(private config: RateLimitConfig) {
    this.tokens = config.maxTokens;
    this.lastRefillTime = Date.now();
    this.startRefilling();
  }

  /**
   * Acquire tokens (blocking)
   */
  async acquire(tokens = 1): Promise<void> {
    while (this.tokens < tokens) {
      const waitTime = this.calculateWaitTime(tokens);
      await this.sleep(waitTime);
      this.refill();
    }

    this.tokens -= tokens;
  }

  /**
   * Try to acquire tokens (non-blocking)
   */
  tryAcquire(tokens = 1): boolean {
    this.refill();

    if (this.tokens >= tokens) {
      this.tokens -= tokens;
      return true;
    }

    return false;
  }

  /**
   * Get current available tokens
   */
  getAvailableTokens(): number {
    this.refill();
    return this.tokens;
  }

  /**
   * Calculate wait time for tokens
   */
  private calculateWaitTime(tokens: number): number {
    const deficit = tokens - this.tokens;
    const tokensPerMs = this.config.refillRate / 1000;
    return Math.ceil(deficit / tokensPerMs);
  }

  /**
   * Refill tokens based on elapsed time
   */
  private refill(): void {
    const now = Date.now();
    const elapsed = now - this.lastRefillTime;
    const tokensToAdd = (elapsed / 1000) * this.config.refillRate;

    this.tokens = Math.min(
      this.tokens + tokensToAdd,
      this.config.maxTokens
    );
    this.lastRefillTime = now;
  }

  /**
   * Start periodic refill
   */
  private startRefilling(): void {
    this.refillTimer = setInterval(() => {
      this.refill();
    }, this.config.refillInterval);
  }

  /**
   * Stop refilling and cleanup
   */
  destroy(): void {
    if (this.refillTimer) {
      clearInterval(this.refillTimer);
    }
  }

  private sleep(ms: number): Promise<void> {
    return new Promise(resolve => setTimeout(resolve, ms));
  }
}

Read the full file on GitHub · 504 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. 2d ago First seen · 504 lines · 29 tokens per session scan A a72baae15910

Subscribe to this mod's changes

rate-limiter-agent is an agent published in the GitHub repository TheLobbi/claude (21 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,809 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 2026-09-05.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens