agent-validator

Don't just review the agent's code — put it through the validator.

Agent Validator (formerly Agent Gauntlet) is a configurable “feedback loop” runner for AI-assisted development workflows.

You configure which paths in your repo should trigger which validations — shell commands like tests and linters, plus AI-powered local code reviews. When files change, Agent Validator automatically runs the relevant validations and reports results.

For AI reviews, it uses the CLI tool of your choice: Gemini, Codex, Claude Code, GitHub Copilot, or Cursor.

Features

• Agent validation loop: Keep your coding agent on track with automated feedback loops. Detect problems — deterministically and/or non-deterministically — and let your agent fix and Agent Validator verify.
• Local cross-agent code reviews: Enable one AI agent to automatically request code reviews from another. For example, if Claude made changes, Agent Validator can request a review from Codex — spreading token usage across your subscriptions instead of burning through one.
  • Multiple AI review adapters have been evaluated for quality and efficiency. Claude and Codex deliver optimal review quality with superior token efficiency. For detailed metrics, see Eval Results.
• Leverage existing subscriptions: Agent Validator is free and tool-agnostic, leveraging the AI CLI tools you already have installed.
• Easy CI setup: Define your CI gates once, run them locally and in GitHub.

Example Workflow

1. Claude implements a feature
2. Agent Validator reports linter failures and bugs detected by Codex reviewer agent
3. Claude fixes issues
4. Agent Validator reports linter issue remaining
5. Claude fixes issue
6. Agent Validator confirms all issues fixed

Common Workflows

Agent Validator supports three workflows, ranging from simple CLI execution to fully autonomous agentic integration:

• CLI Mode — Run checks via command line; ideal for CI pipelines and scripts.
• Assistant Mode — AI assistant runs validation loop, fixing issues iteratively.
• Agentic Mode — Autonomous agent validates and fixes in real-time, delivered as a Claude Code or Cursor plugin. (Coming soon with Agent Runner.)

Comparison vs Other Tools

AI Code Review Tools

Agent Validator is not a replacement for tools that provide AI pull request code reviews. It provides real-time feedback loops for autonomous coding agents, combining deterministic static checks (build, lint, test) with multi-agent AI reviews in a single pipeline. This enables agents to iterate and self-correct until all checks and reviews pass, without human intervention.

Full comparison →

Spec-Driven Workflow Tools

It is recommended to use Agent Validator in conjunction with other spec-driven development tools. We believe is the ideal implementation of the validation step in any Spec → Implement → Validate workflow.

Quick Start

Requirements

• Node.js (v18.0.0+)
• git (change detection and diffs)
• For reviews: one or more supported AI CLIs installed (gemini, codex, claude, github-copilot, cursor). For the full list of tools and how they are used, see CLI Invocation Details

Installation

npm install -g agent-validator

Initialization

Initialize configuration in your project root:

agent-validator init

This walks you through an interactive setup: