autoagent

Community

Design and benchmark AutoAgent experiments

AuthorHandy369
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It helps you run reliable AutoAgent Harbor benchmark and experiment loops while keeping infrastructure stable and ensuring results are analyzed and recorded consistently.

Core Features & Use Cases

  • Experiment planning-first workflow: Uses README.md, program.md, and optional .agent/baseline.md as the source of truth, then directs changes mainly through program.md, tasks/, and run configuration.
  • Two-phase handling (bootstrap vs formal experiments): Separates one-time provider/model compatibility bootstrap from repeatable benchmark iterations.
  • Benchmark-ready output discipline: Directs writing results to isolated experiment output directories (e.g., /Users/handy/autoagent-outputs/<experiment-name>/) and avoiding pollution of the baseline worktree.

Quick Start

Ask for an AutoAgent Harbor benchmark or an A/B test focused on routing/skill evaluation, and tell the agent to update program.md and tasks/ then run and analyze results into a dedicated experiment output folder.

Dependency Matrix

Required Modules

None required

Components

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: autoagent
Download link: https://github.com/Handy369/passto-pi-frame/archive/main.zip#autoagent

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.