Directory · Subagents

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.

★ 1,697 stars · last updated 2025-08-15 · Free, open source · View on GitHub

Best for

• Full-stack developers wanting ready-made domain subagents (React, Next.js, Go, Python, Postgres)
• Trying multi-agent orchestration via the agent-organizer and project CLAUDE.md dispatch
• Adding code review, security audit, and testing specialists to Claude Code

Install

mkdir ~/.claude/agents/lst97
cp /path/to/agents/*.md ~/.claude/agents/lst97

Our take

Based on the scaffold from wshobson/agents and described by the author as for personal use; last push was August 2025. The optional CLAUDE.md dispatch protocol is recommended per project only, and the README warns it can use 2-5x more tokens and over-engineer simple tasks. Several MCP servers (context7, sequential-thinking, magic, playwright) are suggested for full capability, with magic requiring an API key.

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.
• pi-subagents: Pi extension adding Claude Code-style sub-agents, parallel background runs, mid-run steering, and scripted multi-agent workflows.