agent-doe-engine

v0.2.0

A design-of-experiments engine for tuning AI agents. It finds which settings actually change your results, tells you whether each change is real or just run-to-run noise, and picks the best combination when speed, cost, and quality compete. One planned batch of trials instead of guessing or testing one thing at a time.

CodexClaude Code1 Skill

By Tyrone Ross, JrLicense: Apache-2.00 GitHub starsUpdated 3 weeks ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 27, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install agent-doe-engine for Codex and Claude Code

Installs for the current user

codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add agent-doe-engine@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/tyroneross/agent-doe-engine

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

agent-doe-engine/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/agent-doe-engine/SKILL.md

Included Skills1

agent-doe-engineskills/agent-doe-engine/SKILL.md

Use when the user wants to tune an AI agent or optimize one or more measurable numbers at once - "optimize this", "make X faster without blowing up Y", "reduce latency and cost", "find the best trade-off between A and B", "tune these parameters", "which model/prompt/setup", "speed up my app". Runs a Design of Experiments matrix (up to 11 factors in one pass), measures every objective on every run, and selects the best trade-off by weighted scalarization, Derringer-Suich desirability, or Pareto frontier. Falls back to a single-variable autoresearch loop.

Plugin manifests2

.codex-plugin/plugin.json

{
  "name": "agent-doe-engine",
  "version": "0.2.0",
  "description": "A design-of-experiments engine for tuning AI agents. It finds which settings actually change your results, tells you whether each change is real or just run-to-run noise, and picks the best combination when speed, cost, and quality compete. One planned batch of trials instead of guessing or testing one thing at a time.",
  "author": {
    "name": "Tyrone Ross, Jr",
    "url": "https://github.com/tyroneross"
  },
  "repository": "https://github.com/tyroneross/agent-doe-engine",
  "license": "Apache-2.0",
  "homepage": "https://github.com/tyroneross/agent-doe-engine#readme",
  "keywords": [
    "optimization",
    "multi-objective",
    "design-of-experiments",
    "doe",
    "pareto",
    "desirability",
    "factorial",
    "plackett-burman",
    "autoresearch",
    "benchmarking",
    "performance"
  ],
  "commands": "./commands",
  "agents": "./agents",
  "skills": "./skills",
  "interface": {
    "displayName": "Agent DoE Engine",
    "shortDescription": "A design-of-experiments engine for tuning AI agents.",
    "longDescription": "Test many input variables in few runs with Design of Experiments, measure every objective on every run, and pick the best trade-off across competing goals by scalarization, Derringer-Suich desirability, or Pareto frontier. Falls back to a single-variable autoresearch keep/revert loop.",
    "developerName": "Ross Labs",
    "category": "Coding",
    "capabilities": [
      "Read",
      "Write"
    ]
  }
}

.claude-plugin/plugin.json

{
  "name": "agent-doe-engine",
  "version": "0.2.0",
  "description": "A design-of-experiments engine for tuning AI agents. It finds which settings actually change your results, tells you whether each change is real or just run-to-run noise, and picks the best combination when speed, cost, and quality compete. One planned batch of trials instead of guessing or testing one thing at a time.",
  "author": {
    "name": "Tyrone Ross, Jr",
    "url": "https://github.com/tyroneross"
  },
  "repository": "https://github.com/tyroneross/agent-doe-engine",
  "license": "Apache-2.0",
  "homepage": "https://github.com/tyroneross/agent-doe-engine#readme",
  "keywords": [
    "optimization",
    "multi-objective",
    "design-of-experiments",
    "doe",
    "pareto",
    "desirability",
    "factorial",
    "plackett-burman",
    "autoresearch",
    "benchmarking",
    "performance"
  ],
  "skills": "./skills",
  "commands": "./commands",
  "agents": "./agents"
}