Directory · Subagents

Fullcase Web

Reference Next.js + Firebase repo showing parallel AI code review subagents wired up for Claude Code and OpenAI Codex.

★ 93 stars · last updated 2026-04-23 · Free (check license) · View on GitHub

Best for

• Studying how to define quality, performance, and security review subagents in .claude/agents and .codex/agents
• Setting up PR-comment-triggered Claude and Codex reviews via GitHub Actions
• Examples of CLAUDE.md/AGENTS.md rules, review skills, and false-positive suppression files

Install

npm install
cp .env.local.example .env.local
npm run dev

Our take

This is an example project, not a reusable tool: the app is a small test-case manager and the value is in the review configuration files you can copy. Running the CI reviewers requires ANTHROPIC_API_KEY and OPENAI_API_KEY secrets with billing enabled, and the repo has no license, so reuse terms are unclear. The included Firestore and Storage rules are permissive defaults that the README says to tighten before production.

Similar subagents

• Awesome Claude Code Subagents (VoltAgent): A curated collection of 161+ Claude Code subagent definitions across 10 categories, installable as plugins or individual agent files.
• claude-devtools: Desktop and web app that reads local Claude Code session logs to show tool calls, token usage, subagent trees, and context.
• AI Marketing Suite for Claude Code: Claude Code skills and parallel subagents for marketing audits, copywriting, email sequences, ad copy, and client-ready reports.
• pentest-ai-agents: 50 Claude Code subagents turning Claude into an offensive security research assistant for authorized penetration testing.
• Translate Book: Agent skill for Claude Code, Codex, and OpenClaw that translates whole PDF/DOCX/EPUB books using parallel subagents per chunk.
• Claude Code Sub-Agents (lst97): A collection of 33 specialized Claude Code subagents for full-stack development, plus an agent-organizer for multi-agent orchestration.