golem-quota-ts

Enforce distributed resource quotas for TypeScript Golem agents via quota tokens.

Updated May 17, 2026
One-click install
npx skills add https://github.com/Rust-soham/golem-claw --skill golem-quota-ts-rust-soham
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: golem-quota-ts
Source: https://github.com/Rust-soham/golem-claw/tree/main/packages/golem/.agents/skills/golem-quota-ts
Command: npx skills add https://github.com/Rust-soham/golem-claw --skill golem-quota-ts-rust-soham

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Resource-heavy agent workflows need predictable limits so API rate, storage capacity, and connection concurrency don’t overwhelm downstream services or destabilize your deployment.

Core Features & Use Cases

  • Quota configuration in golem.yaml: Define rate, capacity, and concurrency limits per resource (with environment scoping) and choose enforcement actions like reject or throttle.
  • QuotaToken reservations and accounting: Acquire quota tokens once and use withReservation to reserve expected usage and commit actual consumption (including variable-cost workloads like LLM token usage).
  • Agent-to-agent budget splitting: Split a parent token to child agents for controlled delegation and merge returned tokens to restore remaining budget.
  • Runtime quota updates: Adjust resource limits via the CLI so changes take effect for running agents.

Quick Start

Use the golem-quota-ts skill to add a quota definition for your target resource in golem.yaml, acquire the QuotaToken in your agent, and wrap each expensive operation with withReservation to enforce consistent limits.

Frequently Asked Questions about golem-quota-ts

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

FAQPage Schema
How do I enforce resource quotas and rate limiting for TypeScript agents?

You can enforce resource quotas for TypeScript agents by defining rate, capacity, and concurrency limits in a golem.yaml configuration file, then acquiring quota tokens to throttle operations and prevent resource exhaustion.

How does quota token reservation work for variable-cost workloads in distributed scheduling?

Quota token reservation works by acquiring tokens upfront and using the withReservation wrapper to hold expected usage, then committing the actual consumed amount afterward, which handles variable-cost workloads like LLM token usage accurately.

Can I split quota budgets across agent-to-agent RPC calls in TypeScript?

Yes, you can split a parent quota token into child tokens for controlled delegation during agent-to-agent RPC calls, and merge returned tokens back to restore the remaining budget.

Does Golem support runtime updates for concurrency limits and throttling rules?

Golem supports runtime quota updates by adjusting resource limits via the CLI, allowing changes to rate, capacity, and concurrency limits to take effect for currently running agents without restarts.

What is the best way to prevent parallel connections from overwhelming downstream services?

The best way to prevent parallel connections from overwhelming services is to configure distributed concurrency limits with reject or throttle enforcement actions, ensuring agents operate within safe capacity budgets.

Why do I need to define matching resource names in golem.yaml for quota token reservation?

You must define matching resource names in golem.yaml because the quota token reservation system references these definitions to properly allocate bigint amounts and enforce the correct rate or capacity limits per environment.