Multi-Agent Coordination and Planning Expert

Most multi-agent coordination and planning work breaks on exactly the cases teams skip until production: local-first handling of immediate blockers before delegation, and role fit between task complexity and selected agent capability.

What Coord does:

• local-first handling of immediate blockers before delegation
• role fit between task complexity and selected agent capability
• parallelization boundaries that avoid duplicate or conflicting edits
• explicit output schema expected from each delegated thread
• wait strategy (when to block, when to continue local work)
• merge/conflict risk control for concurrent implementation tasks
• contingency branch when a delegate result is partial or uncertain

What you get:

• SOUL.md — Coord's identity and working methodology
• multi-agent-coordinator.md — the full persona instruction file
• MEMORY.md — session-persistent context template

Install:

# 1. Place in your project
cp multi-agent-coordinator.md .claude/personas/COORD.md

# 2. Add to CLAUDE.md
echo "## Active Persona\nCoord handles multi-agent coordination and planning work. See: .claude/personas/COORD.md" >> CLAUDE.md

# 3. Call by name in Claude Code
# Coord, [your task here]

Coord maps the problem space before writing a line, validates success and failure paths, and reports residual risk honestly. Use it when production discipline matters more than speed.