team

Run parallel Claude Code teammate sessions with isolated planning, testing, and reporting.

10|Updated Oct 25, 2025
One-click install
npx skills add https://github.com/fiftynotai/igris-ai --skill team-fiftynotai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team
Source: https://github.com/fiftynotai/igris-ai/tree/main/.claude/skills/team
Command: npx skills add https://github.com/fiftynotai/igris-ai --skill team-fiftynotai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating multiple independent Claude Code instances manually is slow, error-prone, and hard to track; this Skill enables parallel execution of teammates so engineering work like implementing briefs, reviews, investigations, and refactors completes faster with clear ownership and session tracking.

Core Features & Use Cases

  • Spawn Teammates: Create isolated Claude Code teammate sessions that run independent workflows (hunt, review, investigate, refactor) with their own context and tools.
  • Ownership & Safety: Enforce file ownership boundaries, detect file conflicts, require experimental flag CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS, and provide clean shutdown and error handling.
  • Specialized Reviews & Investigations: Run multi-angle reviews (security, performance, standards) or hypothesis-driven investigations across teammates and synthesize unified reports.
  • Session Tracking & Messaging: Maintain ephemeral team state in ai/session/CURRENT_SESSION.md, support messaging/broadcast to teammates, and summarize results on shutdown.

Quick Start

/team hunt FR-022 FR-023 FR-024 to run three briefs in parallel with isolated teammate sessions and file ownership boundaries.

Frequently Asked Questions about team

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run parallel Claude Code sessions for concurrent engineering tasks?

You can run parallel Claude Code sessions by spawning isolated teammate sessions that execute independent engineering workflows concurrently, each with its own context, tools, and file ownership boundaries.

How do I coordinate multiple AI agent teams for code review and investigation?

AI agent teams coordinate code reviews and investigations by assigning specialized angles like security or performance to separate teammates, then synthesizing their isolated findings into a unified report.

Do I need the CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS flag to enable parallel execution?

Yes, enabling the CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS flag is required to activate parallel execution, enforce file ownership boundaries, and ensure clean shutdown procedures for teammate sessions.

How does session tracking work when running multiple Claude Code teammates?

Session tracking for multiple Claude Code teammates maintains ephemeral team state in ai/session/CURRENT_SESSION.md, supporting messaging, broadcast, and result summarization during clean shutdown.

How do I prevent file conflicts during parallel code refactoring with AI teammates?

Parallel code refactoring prevents file conflicts by enforcing strict file ownership boundaries for each teammate session and incorporating automated conflict detection across isolated workflows.