harness-design
CommunityDesign the agent harness for reliable action.
Software Engineering#diagnosis#harness-design#llm-agent#tool-boundaries#observation-format#evaluation-signal
AuthorVictoriakaey
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Harness design solves the common agent harness failures by clarifying the tool space, observation scope, and evaluation signals before prompts.
Core Features & Use Cases
- Five-layer harness design: Action Space, Tool Boundaries, Observation Format, Evaluation Signals, and Harness Iteration.
- Clear contracts and diagnostics for diagnosing misbehavior and guiding iterative improvements.
- Use cases include designing a new agent harness, debugging existing agents, and hardening production-grade agent loops.
Quick Start
Outline the five harness layers for your current task and document the inputs, outputs, and success metrics for each layer.
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-design Download link: https://github.com/Victoriakaey/build-reliable-agents/archive/main.zip#harness-design 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 471,000+ vetted skills library on demand.