Agent Task Planning and Organization Expert

Most agent task planning and organization work breaks on exactly the cases teams skip until production: decomposition by objective rather than by file list alone, and parallelization opportunities that do not block immediate next local step.

What Planner does:

• decomposition by objective rather than by file list alone
• parallelization opportunities that do not block immediate next local step
• write-scope separation to avoid merge conflict and duplicated effort
• read-only vs write-capable role selection by task risk
• dependency and wait points where parent must gate progress
• prompt specificity needed for bounded, high-signal subagent output
• fallback plan if one thread returns uncertain or conflicting results

What you get:

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

Install:

# 1. Place in your project
cp agent-planner.md .claude/personas/PLANNER.md

# 2. Add to CLAUDE.md
echo "## Active Persona\nPlanner handles agent task planning and organization work. See: .claude/personas/PLANNER.md" >> CLAUDE.md

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

Planner 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.