create-agent-adapter

Create Paperclip agent adapters implementing execute, sessionCodec, and testEnvironment contracts.

Updated Mar 15, 2026
One-click install
npx skills add https://github.com/mighty-hq/mighty-paperclip --skill create-agent-adapter-mighty-hq
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-agent-adapter
Source: https://github.com/mighty-hq/mighty-paperclip/tree/main/.agents/skills/create-agent-adapter
Command: npx skills add https://github.com/mighty-hq/mighty-paperclip --skill create-agent-adapter-mighty-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you design and implement a new Paperclip agent adapter so Paperclip can orchestrate, display, and run your custom agent runtime reliably.

Core Features & Use Cases

  • Adapter Architecture Blueprint: Defines the required server, UI, and CLI module structure and how each part is consumed by Paperclip.
  • Typed Execution & Parsing Contract: Specifies the execute and stdout parsing expectations, including session handling, usage/cost reporting, and defensive parsing.
  • Registration & Session Management Guidance: Covers how to register adapters in server/UI/CLI registries and how to implement session codecs for long-running work.
  • Safe Skill Injection Patterns: Explains how to expose shared Paperclip skills to the agent runtime without contaminating the user’s working directory.

Quick Start

Use the create-agent-adapter skill guide to build a new adapter package for your agent runtime by implementing the required exports and registries following the adapter-utils interfaces.

Frequently Asked Questions about create-agent-adapter

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

FAQPage Schema
How do I build a custom agent adapter for TypeScript CLI streaming?

To build a custom agent adapter, implement the server execute and sessionCodec contracts alongside UI and CLI registry modules using adapter-utils shared types to bridge orchestration and CLI streaming output.

What is agent adapter session management and when do I need session codecs?

Agent adapter session management handles long-running work by persisting state via session codecs, which are required when your custom agent runtime needs continuous orchestration and UI transcript parsing across multiple interactions.

Can I use this adapter architecture to bridge HTTP endpoint agents?

Yes, this adapter architecture supports creating adapter packages for local CLIs, HTTP endpoint agents, and custom processes by implementing the required testEnvironment and output parsing contracts.

What's the best way to parse stdout output from a custom agent runtime?

The best way to parse stdout output is to follow the typed execution contract with defensive parsing practices, ensuring reliable extraction of usage and cost reporting data from your agent runtime streams.

How do I inject shared skills into an agent runtime without contaminating the working directory?

Safe skill injection patterns expose shared Paperclip skills to the agent runtime through isolated mechanisms that prevent file contamination, keeping the user's working directory clean during orchestration.