{"id":45673566,"url":"https://github.com/hamelsmu/claude-review-loop","last_synced_at":"2026-05-04T13:40:35.238Z","repository":{"id":339705441,"uuid":"1163037979","full_name":"hamelsmu/claude-review-loop","owner":"hamelsmu","description":"Claude Code plugin: automated code review loop with Codex","archived":false,"fork":false,"pushed_at":"2026-02-22T04:26:09.000Z","size":42,"stargazers_count":549,"open_issues_count":1,"forks_count":29,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-03-09T19:51:56.468Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hamelsmu.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-21T02:13:01.000Z","updated_at":"2026-03-09T15:59:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/hamelsmu/claude-review-loop","commit_stats":null,"previous_names":["hamelsmu/claude-review-loop"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hamelsmu/claude-review-loop","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hamelsmu%2Fclaude-review-loop","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hamelsmu%2Fclaude-review-loop/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hamelsmu%2Fclaude-review-loop/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hamelsmu%2Fclaude-review-loop/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hamelsmu","download_url":"https://codeload.github.com/hamelsmu/claude-review-loop/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hamelsmu%2Fclaude-review-loop/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32610261,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"ssl_error","status_checked_at":"2026-05-04T10:08:02.005Z","response_time":58,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-02-24T12:00:24.256Z","updated_at":"2026-05-04T13:40:35.231Z","avatar_url":"https://github.com/hamelsmu.png","language":"Shell","funding_links":[],"categories":["🔌 Claude Plugins","Cross-LLM Collaboration"],"sub_categories":[],"readme":"# review-loop\n\nA Claude Code plugin that adds an automated code review loop to your workflow.\n\n## What it does\n\nWhen you use `/review-loop`, the plugin creates a two-phase lifecycle:\n\n1. **Task phase**: You describe a task, Claude implements it\n2. **Review phase**: When Claude finishes, the stop hook prepares a [Codex](https://github.com/openai/codex) runner script and blocks exit. Claude then runs Codex directly (with output streaming to the user) and addresses the review feedback.\n\nThe result: every task gets an independent second opinion before you accept the changes, and you can watch the review happen in real time.\n\n\u003cimg width=\"2284\" height=\"1959\" alt=\"memelord_meme_2026-02-22 (3)\" src=\"https://github.com/user-attachments/assets/75af1351-47e6-4b70-a50a-9b3311773be7\" /\u003e\n\n\n## Review coverage\n\nThe plugin spawns up to 4 parallel Codex sub-agents, depending on project type:\n\n| Agent | Always runs? | Focus |\n|-------|-------------|-------|\n| **Diff Review** | Yes | `git diff` — code quality, test coverage, security (OWASP top 10) |\n| **Holistic Review** | Yes | Project structure, documentation, AGENTS.md, agent harness, architecture |\n| **Next.js Review** | If `next.config.*` or `\"next\"` in `package.json` | App Router, Server Components, caching, Server Actions, React performance |\n| **UX Review** | If `app/`, `pages/`, `public/`, or `index.html` exists | Browser E2E via [agent-browser](https://agent-browser.dev/), accessibility, responsive design |\n\nAfter all agents finish, Codex deduplicates findings and writes a single consolidated review to `reviews/review-\u003cid\u003e.md`.\n\n## Requirements\n\n- [Claude Code](https://claude.ai/code) (CLI)\n- `jq` — `brew install jq` (macOS) / `apt install jq` (Linux)\n- [Codex CLI](https://github.com/openai/codex) — `npm install -g @openai/codex`\n\n### Codex multi-agent\n\nThis plugin uses Codex [multi-agent](https://developers.openai.com/codex/multi-agent/) to run parallel review agents. The `/review-loop` command automatically enables it in `~/.codex/config.toml` on first use.\n\nTo set it up manually instead:\n\n```toml\n# ~/.codex/config.toml\n[features]\nmulti_agent = true\n```\n\n## Installation\n\nFrom the CLI:\n\n```bash\nclaude plugin marketplace add hamelsmu/claude-review-loop\nclaude plugin install review-loop@hamel-review\n```\n\nOr from within a Claude Code session:\n\n```\n/plugin marketplace add hamelsmu/claude-review-loop\n/plugin install review-loop@hamel-review\n```\n\n\n## Updating\n\n```bash\nclaude plugin marketplace update hamel-review\nclaude plugin update review-loop@hamel-review\n```\n\n## Usage\n\n### Start a review loop\n\n```\n/review-loop Add user authentication with JWT tokens and test coverage\n```\n\nClaude will implement the task. When it finishes, the stop hook:\n1. Prepares a Codex runner script and prompt file\n2. Blocks Claude's exit with instructions to run the review\n3. Claude runs `bash .claude/review-loop-run-codex.sh` — Codex output streams to the user\n4. Codex writes findings to `reviews/review-\u003cid\u003e.md`\n5. Claude reads the review, addresses items it agrees with, then stops\n\n### Cancel a review loop\n\n```\n/cancel-review\n```\n\n## How it works\n\nThe plugin uses a **Stop hook** — Claude Code's mechanism for intercepting agent exit. When Claude tries to stop:\n\n1. The hook reads the state file (`.claude/review-loop.local.md`)\n2. If in `task` phase: writes a runner script and prompt file, transitions to `addressing`, blocks exit with instructions for Claude to run Codex\n3. If in `addressing` phase: allows exit and cleans up\n\nState is tracked in `.claude/review-loop.local.md` (add to `.gitignore`). Reviews are written to `reviews/review-\u003cid\u003e.md`.\n\n## File structure\n\n```\nclaude-review-loop/\n├── .claude-plugin/\n│   └── plugin.json           # Plugin manifest\n├── commands/\n│   ├── review-loop.md        # /review-loop slash command\n│   └── cancel-review.md      # /cancel-review slash command\n├── hooks/\n│   ├── hooks.json            # Stop hook registration (30s timeout)\n│   └── stop-hook.sh          # Core lifecycle engine\n├── scripts/\n│   └── setup-review-loop.sh  # Argument parsing, state file creation\n├── AGENTS.md                  # Agent operating guidelines\n├── CLAUDE.md                  # Symlink to AGENTS.md\n└── README.md\n```\n\n## Configuration\n\nThe 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.\n\n### Environment variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `REVIEW_LOOP_CODEX_FLAGS` | `--dangerously-bypass-approvals-and-sandbox` | Flags passed to `codex`. Set to `--sandbox workspace-write` for safer sandboxed reviews. |\n\n### Telemetry\n\nExecution logs are written to `.claude/review-loop.log` with timestamps, codex exit codes, and elapsed times. This file is gitignored.\n\n## Credits\n\nInspired by the [Ralph Wiggum plugin](https://github.com/anthropics/claude-code/tree/main/plugins/ralph-wiggum) and [Ryan Carson's compound engineering loop](https://x.com/ryancarson/article/2016520542723924279).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhamelsmu%2Fclaude-review-loop","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhamelsmu%2Fclaude-review-loop","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhamelsmu%2Fclaude-review-loop/lists"}