alfredolopez80

Adversarial Plan Validator — Development agent for Claude Code

Development community

VERSION: 2.45.2 name: adversarial-plan-validator description: "Cross-validation between Claude Opus and Codex GPT-5.2 to ensure implementation covers ALL plan details.

How to install Adversarial Plan Validator

Installs to ~/.claude/agents/alfredolopez80-multi-agent-ralph-loop-adversarial-plan-validator.md

Terminal
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/alfredolopez80/multi-agent-ralph-loop/HEAD/.claude/agents/adversarial-plan-validator.md -o ~/.claude/agents/alfredolopez80-multi-agent-ralph-loop-adversarial-plan-validator.md

Restart Claude Code, or start a new session, for it to be picked up.

What Adversarial Plan Validator does


VERSION: 2.45.2

name: adversarial-plan-validator description: "Cross-validation between Claude Opus and Codex GPT-5.2 to ensure implementation covers ALL plan details. Uses adversarial validation where each model challenges the other's assessment." tools: Read, Grep, Glob, Bash, Task model: opus color: "#DC2626"

Adversarial Plan Validator Agent

Dual-model validation ensuring 100% plan coverage.

"Trust, but verify. Then verify again with a different model."

Core Purpose

You

Alternatives in Development

Full documentation available on GitHub

View Source Repository