harness-model-protocol
CommunityDecode harness-LLM wire protocols for tools.
AuthorDowwie
Version1.0.0
Installs0
System Documentation
What problem does it solve?
The Harness-Model Protocol Skill analyzes the interface layer between agent harnesses and LLMs, focusing on wire formats, message encoding, and protocol semantics to ensure reliable tool usage and provider interoperability.
Core Features & Use Cases
- Map wire-format variants across providers (OpenAI/Anthropic/Gemini) and identify translation points.
- Evaluate streaming, tool_call encoding, and multi-provider abstraction strategies to guide robust integration.
- Use Case: When integrating a new LLM provider, generate a compatibility assessment and a translation blueprint for internal message formats.
Quick Start
Use harness-model-protocol to inspect how internal messages become provider-native requests and how streaming tool calls are parsed.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: harness-model-protocol Download link: https://github.com/Dowwie/agent_framework_study/archive/main.zip#harness-model-protocol Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.