golem-fire-and-forget-ts

Trigger TypeScript Golem agent methods asynchronously with .trigger().

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fire-and-forget agent calls let you enqueue work without blocking the current agent, avoiding deadlocks and improving responsiveness when a result is not immediately needed.

Core Features & Use Cases

  • Async trigger invocation: Use the client’s .trigger() variant to enqueue a target agent method and return immediately.
  • Deadlock avoidance patterns: Use triggers for callbacks so Agent A can keep going while Agent B notifies without waiting.
  • Fan-out and event-driven workflows: Trigger many agent tasks in parallel or react to events without coupling to downstream processing time.

Quick Start

Use the golem-fire-and-forget-ts guidance to tell your agent client to call .trigger() on the method you want to enqueue, for example by invoking CounterAgent.get("my-counter").increment.trigger() when you want the call to run without waiting.

Frequently Asked Questions about golem-fire-and-forget-ts

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

FAQPage Schema
How do I trigger async agent calls in TypeScript without blocking the current process?

To trigger async agent calls without blocking, use the generated client method `.trigger()` instead of awaiting the invocation. This enqueues the target agent method and returns immediately, allowing your current agent to continue processing. It applies to TypeScript Golem projects.

How does fire-and-forget invocation help avoid deadlocks in Golem agent workflows?

Fire-and-forget invocation avoids deadlocks by enabling async callbacks where Agent A triggers Agent B and continues without waiting. This prevents cyclic waits, allowing event-driven workflows and parallel fan-out tasks to execute independently without coupling to downstream processing time.

What is the best way to perform parallel fan-out across multiple Golem agents?

The best way to perform parallel fan-out is using the `.trigger()` method on your target agents. By triggering multiple agent tasks in parallel, you enqueue work instantly without blocking the caller, enabling responsive event-driven workflows.

Can I use the fire-and-forget trigger behavior from the command line?

Yes, you can use the fire-and-forget trigger behavior from the command line. The `.trigger()` client method supports the enqueue behavior equivalent to the `golem agent invoke --enqueue` command, allowing you to queue agent work via CLI workflows.

When should I not use fire-and-forget triggers for agent invocations?

You should not use fire-and-forget triggers when the current agent immediately depends on the result of the target agent method. Because `.trigger()` returns instantly without waiting, it is only suited for async callbacks and background work where the result is not needed right away.