whereismyai
Reviewer Agent
Reviewer Agent is an automated commit review and stop supervision tool for Claude Code and Codex.
Reviewer Agent provides automated plan and code reviews to gate git commits until issues are resolved. It also features stop-continue supervision to evaluate project plans and task lists, preventing coding agents from stopping prematurely or asking redundant questions. The package supports Claude Code and Codex, using Codex, Pi, or Claude Code as the reviewer agent. It runs independent commit reviews, checks staged diffs, manages stop-continue supervision, and includes a watchdog to automatically re-prompt stalled sessions. Users can configure model choices, reasoning effort, and project-specific briefs to fit their workflows.
Reviewer Agent at a glance
Key features
- Commit review gating
- Stop-continue supervision
- Stop-continue watchdog
- Multi-model reviewer selection
- Agentic Codex review with sandbox test execution
- Delta re-review on retries
- Skimmed paths configuration
- Per-project reviewer brief
Use it for
- Reviewing code and plans before allowing git commits
- Preventing coding agents from stopping prematurely
- Re-prompting stalled or idle sessions automatically
- Configuring project-specific reviewer instructions
Companions
Tools that articles about Reviewer Agent recommend using with it, each with its job.
- Claude Code — Built to work with Claude Code.
- Codex — Built to work with Codex.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Superpowers — Brainstorm, plan and execute skills for bigger tasks.
- Playwright MCP — Enables LLMs to interact with web pages using structured accessibility snapshots.
- GitHub MCP Server — Reads pull requests, issues and code search on GitHub.
Alternatives to Reviewer Agent
- agent.reviews — Real tool reviews written directly by coding agents after task completion.
- Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
- Git AutoReview — Parallel AI reviews with human approval and bring-your-own-key security.
- CodeRabbit — Most-installed AI PR reviewer, built to check code from coding agents
- Codex Plugin for Claude Code — Delegate tasks and run code reviews with Codex directly inside Claude Code.
- Stop That Shit — Enforces task boundaries to stop unnecessary AI agent actions.
- Greptile — Catches multi-file bugs by reviewing beyond the diff
- Flash Agents — Offloads reading and typing to cheap workers while keeping Claude for review
- Agent Pets — Approve agent permission prompts and send replies directly from any browser tab
- Simple Reviewer V1 — Explains AI code and checks behavior using recorded evidence.
- Agent Skills — Encodes senior-engineer workflows and quality gates into 24 skills.
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
All Reviewer Agent alternatives