Automated code review loop plugin for Claude Code
npx claudepluginhub hamelsmu/claude-review-loopAutomated code review loop: Claude implements, Codex reviews independently, Claude addresses feedback
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations
Curated collection of 141 specialized Claude Code subagents organized into 10 focused categories
Share bugs, ideas, or general feedback.
A Claude Code plugin that adds an automated code review loop to your workflow.
When you use /review-loop, the plugin creates a two-phase lifecycle:
The result: every task gets an independent second opinion before you accept the changes, and you can watch the review happen in real time.
The plugin spawns up to 4 parallel Codex sub-agents, depending on project type:
| Agent | Always runs? | Focus |
|---|---|---|
| Diff Review | Yes | git diff — code quality, test coverage, security (OWASP top 10) |
| Holistic Review | Yes | Project structure, documentation, AGENTS.md, agent harness, architecture |
| Next.js Review | If next.config.* or "next" in package.json | App Router, Server Components, caching, Server Actions, React performance |
| UX Review | If app/, pages/, public/, or index.html exists | Browser E2E via agent-browser, accessibility, responsive design |
After all agents finish, Codex deduplicates findings and writes a single consolidated review to reviews/review-<id>.md.
jq — brew install jq (macOS) / apt install jq (Linux)npm install -g @openai/codexThis plugin uses Codex multi-agent to run parallel review agents. The /review-loop command automatically enables it in ~/.codex/config.toml on first use.
To set it up manually instead:
# ~/.codex/config.toml
[features]
multi_agent = true
From the CLI:
claude plugin marketplace add hamelsmu/claude-review-loop
claude plugin install review-loop@hamel-review
Or from within a Claude Code session:
/plugin marketplace add hamelsmu/claude-review-loop
/plugin install review-loop@hamel-review
claude plugin marketplace update hamel-review
claude plugin update review-loop@hamel-review
/review-loop Add user authentication with JWT tokens and test coverage
Claude will implement the task. When it finishes, the stop hook:
bash .claude/review-loop-run-codex.sh — Codex output streams to the userreviews/review-<id>.md/cancel-review
The plugin uses a Stop hook — Claude Code's mechanism for intercepting agent exit. When Claude tries to stop:
.claude/review-loop.local.md)task phase: writes a runner script and prompt file, transitions to addressing, blocks exit with instructions for Claude to run Codexaddressing phase: allows exit and cleans upState is tracked in .claude/review-loop.local.md (add to .gitignore). Reviews are written to reviews/review-<id>.md.
claude-review-loop/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── commands/
│ ├── review-loop.md # /review-loop slash command
│ └── cancel-review.md # /cancel-review slash command
├── hooks/
│ ├── hooks.json # Stop hook registration (30s timeout)
│ └── stop-hook.sh # Core lifecycle engine
├── scripts/
│ └── setup-review-loop.sh # Argument parsing, state file creation
├── AGENTS.md # Agent operating guidelines
├── CLAUDE.md # Symlink to AGENTS.md
└── README.md
The stop hook timeout is set to 30 seconds in hooks/hooks.json. The hook itself is fast (it only writes files and returns a block decision); Codex runs separately via Claude's Bash tool.
| Variable | Default | Description |
|---|---|---|
REVIEW_LOOP_CODEX_FLAGS | --dangerously-bypass-approvals-and-sandbox | Flags passed to codex. Set to --sandbox workspace-write for safer sandboxed reviews. |
Execution logs are written to .claude/review-loop.log with timestamps, codex exit codes, and elapsed times. This file is gitignored.