quota-manager

Track client-side quotas and compute wait times for Gemini Deep Research API calls.

Updated Dec 21, 2025
One-click install
npx skills add https://github.com/rickoslyder/TraitorSim --skill quota-manager
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: quota-manager
Source: https://github.com/rickoslyder/TraitorSim/tree/main/.claude/skills/quota-manager
Command: npx skills add https://github.com/rickoslyder/TraitorSim --skill quota-manager

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Gemini Deep Research quotas are opaque and dynamic. This Skill provides client-side tracking, exponential backoff, and wave-based submission strategies to minimize quota errors and maximize throughput.

Core Features & Use Cases

  • Quota tracking: Local RPM/RPD accounting to plan submissions.
  • Backoff strategies: Exponential backoff for retrying quota hits.
  • Wave-based submission: Submit in predefined waves to align with observed quota patterns.

Quick Start

Create a QuotaTracker and wrap API calls with a check for available quota, then back off or wait as needed.

Frequently Asked Questions about quota-manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement rate limiting for Gemini API calls?

Rate limiting for Gemini API calls involves tracking requests per minute and per day using client-side quota accounting. Create a QuotaTracker to monitor consumption against your account tier's limits, then gate API submissions to stay within those boundaries and avoid quota errors.

What is exponential backoff and when should I use it for API quota hits?

Exponential backoff is a retry strategy that increases wait time between attempts after hitting quota limits. When Gemini rejects a submission due to quotas, exponential backoff automatically spaces retries further apart, reducing contention and improving success rates on subsequent tries.

Can I submit batch jobs without hitting Gemini quota limits?

Yes. Wave-based submission strategies align batch job submissions with observed quota patterns to minimize rejections. By submitting in predefined waves rather than all at once, you distribute load across quota windows and maximize throughput on free and paid tiers.

How do I track per-minute and per-day quotas for Gemini Deep Research?

Use client-side quota tracking to maintain local RPM and RPD counters. QuotaTracker computes available quota and required wait times before each submission, letting you plan when requests will succeed without server-side rejection.

Do I need to know my exact Gemini quota limits in advance?

No. This approach handles opaque and dynamic quotas through client-side tracking and adaptive backoff. You provide your account tier, and the system learns submission patterns and enforces limits locally without requiring pre-published quota numbers.

What's the best way to integrate quota management into batch submission workflows?

Wrap batch submissions with quota checks before each request. QuotaTracker integration lets you verify available quota, apply backoff delays when needed, and coordinate wave-based submission timing to stay compliant across the entire job lifecycle.