A practical example of integrating AI code review into a real-world codebase. Built with Next.js and Firebase, this repo highlights structured prompts, reusable review skills, and parallel subagent execution via Claude Code and OpenAI Codex.
11 files for Claude Code, Codex, OpenCode and Gemini CLI: code-review, update-review-checklist, code-quality-pr-reviewer, code-reviewer and 7 more — 14,727 tokens loaded in every session.
AGENTS.md A 9,273 tok CLAUDE.md A 2,678 tok GEMINI.md A 2,776 tok .claude/settings.json A — .agents/skills/code-review/SKILL.md A 21 tok .agents/skills/update-review-checklist/SKILL.md A 27 tok .claude/commands/review-pr.md A 20 tok .claude/agents/code-quality-pr-reviewer.md A 31 tok .claude/agents/code-reviewer.md A 44 tok .claude/agents/performance-pr-reviewer.md A 26 tok .claude/agents/security-code-pr-reviewer.md A 29 tok These files are dalemoncayo/fullcase-web's own configuration — they tell Claude Code, Codex, OpenCode and Gemini CLI how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.