builder-api-reference

Compose ReactiveAgent builder chains with .withX() methods for TypeScript projects.

21|4|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill builder-api-reference
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: builder-api-reference
Source: https://github.com/tylerjrbuell/reactive-agents-ts/tree/main/apps/docs/skills/builder-api-reference
Command: npx skills add https://github.com/tylerjrbuell/reactive-agents-ts --skill builder-api-reference

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a centralized, authoritative reference and examples to assemble complete and correctly ordered ReactiveAgent builder chains so developers avoid missing methods, misordered calls, or incorrect parameter shapes when constructing agents.

Core Features & Use Cases

  • Complete Method Catalog: Enumerates .withX() methods, expected parameter shapes, defaults, and return behaviors across identity, provider, reasoning, tools, memory, safety, cost, observability, persistence, and build APIs.
  • Practical Implementations: Shows minimal and production-ready builder chains that demonstrate reliability, observability, cost routing, guardrails, and memory configuration.
  • Use Case: Build a production-ready assistant that uses an external provider, a specific model, adaptive reasoning with iteration limits, enhanced memory backed by SQLite, runtime guardrails, verification, and cost tracking for safe, auditable deployments.

Quick Start

Compose an agent builder that names the agent assistant, sets provider to anthropic, selects model claude-opus-4-6, enables adaptive reasoning with maxIterations 15, configures enhanced memory at ./agent.db, turns on guardrails and verification, enables cost tracking with perRequest 0.50, and enables live observability.

Frequently Asked Questions about builder-api-reference

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

FAQPage Schema
How do I compose a correctly ordered ReactiveAgent builder chain in TypeScript?

ReactiveAgent builder chains require a specific method ordering across identity, provider, reasoning, tools, memory, safety, cost, and observability APIs. Sequencing .withX() calls correctly prevents misordered configurations and invalid parameter shapes during agent construction.

What parameter shapes and defaults are required when configuring ReactiveAgent builders?

ReactiveAgent builders require specific parameter shapes, defaults, required fields, and return behaviors for .withX() calls across identity, provider, reasoning, tools, memory, safety, cost, and observability APIs. Matching these parameter shapes ensures correct build and runtime behaviors.

How do I configure adaptive reasoning, memory, and guardrails in a production-ready ReactiveAgent?

You configure a production-ready ReactiveAgent by chaining .withX() methods to enable adaptive reasoning with iteration limits, enhanced SQLite-backed memory, runtime guardrails, verification, cost tracking, and live observability for a safe and auditable deployment.

Does the @reactive-agents/core builder API support external providers like Anthropic and cost tracking?

The @reactive-agents builder API supports external providers like Anthropic, model selection, and cost tracking with per-request limits. These configurations are applied using available .withX() builder calls for correct, production-ready agent construction.

What are common limitations or issues when misordering ReactiveAgent builder methods?

Misordering ReactiveAgent builder methods leads to missing configurations, misordered calls, and incorrect parameter shapes that break agent construction. Referencing a complete method catalog prevents these errors by enforcing correct method-level accuracy and parameter shapes.