incur

Create TypeScript CLIs with strict schemas and structured output envelopes.

590|33|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/wevm/incur --skill incur
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: incur
Source: https://github.com/wevm/incur/tree/main
Command: npx skills add https://github.com/wevm/incur --skill incur

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

incur provides a TypeScript framework for building CLIs that work for both AI agents and humans, with strong typing, structured envelopes, and built-in discovery.

Core Features & Use Cases

  • Strictly typed schemas for arguments and options to prevent runtime errors.
  • Structured output envelopes that work for humans and agents, with formats like TOON, JSON, YAML, and MD.
  • Agent discovery via Skills, MCP, and --llms to streamline integration and onboarding.
  • Auto-generated skill files to simplify agent integration and documentation.

Quick Start

Define a CLI with Cli.create(), add commands with .command(), and serve it with .serve().

Frequently Asked Questions about incur

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

FAQPage Schema
How do I build TypeScript CLIs that are safe for AI agents to discover and use?

You can build TypeScript CLIs for AI agents by defining strictly typed schemas for arguments and options, generating structured output envelopes, and utilizing built-in agent discovery via Skills and MCP.

What is the best way to generate CLI documentation for LLMs in TypeScript?

The best way to generate CLI documentation for LLMs is to auto-generate skill files from strictly typed schemas, enabling seamless agent integration, onboarding, and discovery through formats like TOON, JSON, YAML, and MD.

How do I prevent runtime errors from inconsistent CLI definitions in TypeScript?

Prevent runtime errors from inconsistent CLI definitions by applying strict input and output schemas to your TypeScript commands, ensuring arguments and options are validated before execution.

Can I format CLI output as both human-readable text and structured data for agents?

Yes, you can format CLI output for both humans and agents by utilizing structured output envelopes that support multiple formats including TOON, JSON, YAML, and Markdown.

Does this TypeScript CLI framework support MCP and auto-discovery?

Yes, this TypeScript CLI framework supports MCP and auto-discovery by generating skill files and utilizing the --llms flag to streamline integration and onboarding for AI agents.