Agent Teams

This is an opinionated, zero-compromise TDD workflow that treats every Claude Code project as a coordinated team of AI agents. You get five permanent agents (team lead, quality, security, code review, merger) plus one feature agent per feature, all locked into a strict 10-step pipeline: spec, review, write failing tests, verify they fail, implement, verify they pass, validate, code review, security scan, then branch and PR. No step can be skipped because task dependencies enforce the chain. The quality agent physically blocks implementation until tests exist and fail, then blocks merging until they pass with 80% coverage. It's heavyweight by design, best for teams that want automated rigor and are willing to accept the ceremony. If you just want to ship a quick fix, this will feel like overkill.

skills.sh installs: 186
GitHub stars: 685
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add alinaqi/claude-bootstrap --skill agent-teams --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Teams Skill

Purpose: Every project initialized with Maggy runs as a coordinated team of AI agents. This is the default workflow, not optional. Teams enforce a strict TDD pipeline where no step can be skipped.

Setup: Agent definitions go in .claude/agents/ with proper frontmatter (name, description, model, tools, disallowedTools, maxTurns, effort). See agent files for the format.