Planning with Teams
Manus-style context engineering for Claude Code Agent Teams. Coordinate multiple Claude instances with shared planning files, structured task assignment, and persistent working memory.
Prerequisites
Agent Teams must be enabled:
# In your shell or settings.json
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Without this, Claude cannot spawn teammates. The skill will fall back to subagent mode.
The Core Insight
Agent Teams give each teammate their own context window. But without coordination:
- Teammates forget the overall goal
- Findings get lost between agents
- Work gets duplicated or conflicts
Solution: Apply Manus principles to multi-agent coordination.
Single Agent: Context Window = RAM (volatile)
Filesystem = Disk (persistent)
Agent Team: Each Agent = Separate RAM
Shared Files = Shared Disk
→ Shared planning files become the team's "collective memory"
Quick Start
Before ANY team-based task:
- Create
team_plan.md— Shared roadmap all teammates reference - Create
team_findings.md— Shared discovery log - Create
team_progress.md— Shared session log - Spawn team with clear roles — Each teammate owns specific phases
- Teammates re-read plan before decisions — Keeps everyone aligned
Critical: All files go in YOUR PROJECT directory, not the skill folder.
File Locations
| Location | What Goes There |
|---|---|
Skill directory (${CLAUDE_PLUGIN_ROOT}/) | Templates, scripts, reference docs |
| Your project directory | team_plan.md, team_findings.md, team_progress.md |
~/.claude/teams/{team-name}/ | Anthropic's team config (auto-managed) |
~/.claude/tasks/{team-name}/ | Anthropic's shared task list (auto-managed) |
The Team Coordination Pattern
Phase 1: Team Lead Creates Plan
Before spawning teammates, the lead creates the shared planning files:
# Create team_plan.md with phases assigned to teammates
Write team_plan.md
# Create empty findings and progress files
Write team_findings.md
Write team_progress.md
Phase 2: Spawn Team with Clear Roles
Create an agent team for [TASK]:
Teammate 1 (researcher):
- Owns Phase 1: Discovery and requirements
- Writes findings to team_findings.md
- Model: haiku (fast, cheap for research)
Teammate 2 (implementer):
- Owns Phase 2-3: Design and implementation
- Reads team_findings.md before starting
- Model: sonnet (balanced)
Teammate 3 (reviewer):
- Owns Phase 4: Testing and verification
- Challenges findings, looks for issues
- Model: sonnet (needs reasoning)
Phase 3: Teammates Follow Manus Rules
Each teammate MUST:
- Read team_plan.md before major decisions — Re-orients to team goal
- Write discoveries to team_findings.md — Shared knowledge
- Update team_progress.md after actions — Visibility for lead
- Apply 3-Strike Error Protocol — Log failures, don't repeat
- Message lead when phase complete — Coordination
Phase 4: Lead Synthesizes
When teammates finish:
- Read all shared files
- Synthesize findings
- Resolve any conflicts
- Deliver final result
Team Roles
| Role | Responsibility | When to Use |
|---|---|---|
| Lead | Coordinates, synthesizes, owns team_plan.md | Always needed |
| Researcher | Explores, gathers context, documents findings | Research-heavy tasks |
| Implementer | Writes code, creates deliverables | Feature development |
| Reviewer | Tests, validates, challenges assumptions | Quality-critical work |
| Devil's Advocate | Questions decisions, finds edge cases | Complex design tasks |
Critical Rules
Rule 1: Shared Files Are Sacred
All teammates read from and write to the SAME files:
team_plan.md— Single source of truth for phasesteam_findings.md— All discoveries go hereteam_progress.md— All activity logged here
Rule 2: Re-Read Before Decide
Each teammate re-reads team_plan.md before major decisions:
[Teammate has done many tool calls...]
[Original team goal may be forgotten...]
→ Read team_plan.md # Goal refreshed in attention!
→ Now make decision # Aligned with team objective
Rule 3: Write Findings Immediately
After ANY discovery (code found, error hit, decision made):
Edit team_findings.md # Add finding immediately
Don't wait. Context is volatile. Disk is persistent.
Rule 4: The 2-Action Rule (Per Teammate)
"After every 2 view/browser/search operations, IMMEDIATELY save findings."
This applies to EACH teammate individually.
Rule 5: No Duplicate Work
Before starting work, teammates check team_findings.md:
Read team_findings.md # Has someone already found this?
Rule 6: Message on Phase Complete
When a teammate finishes their phase:
Message lead: "Phase X complete. Key findings in team_findings.md section Y.
Ready for Phase X+1 or need review."
Team Plan Structure
# Team Plan: [Task Description]
## Goal
[One sentence — the north star for ALL teammates]
## Team Composition
| Teammate | Role | Phases Owned | Model |
|----------|------|--------------|-------|
| Lead | Coordinator | Synthesis | inherit |
| Agent-1 | Researcher | 1 | haiku |
| Agent-2 | Implementer | 2, 3 | sonnet |
| Agent-3 | Reviewer | 4 | sonnet |
## Current Status
- Phase 1: complete (Agent-1)
- Phase 2: in_progress (Agent-2)
- Phase 3: pending
- Phase 4: pending
## Phases
### Phase 1: Discovery [Agent-1]
- [ ] Research existing code
- [ ] Document patterns found
- [ ] Identify constraints
- **Status:** complete
- **Findings:** See team_findings.md#discovery
### Phase 2: Design [Agent-2]
- [ ] Review Phase 1 findings
- [ ] Create implementation plan
- [ ] Get lead approval if needed
- **Status:** in_progress
When to Use Agent Teams
Use teams for:
- Parallel code review (security + performance + tests)
- Research with competing hypotheses
- Feature development (frontend + backend + tests)
- Large refactoring (multiple modules)
- Cross-layer changes
Don't use teams for:
- Simple single-file edits
- Sequential dependent work
- Tasks under 5 tool calls
- Same-file modifications (conflict risk)
Display Modes
Set in your Claude Code settings:
| Mode | How | Best For |
|---|---|---|
| in-process | --teammate-mode in-process | Any terminal, default |
| split-panes | --teammate-mode tmux | tmux/iTerm2, visual monitoring |
In-process: Use Shift+Up/Down to select teammates, Ctrl+T for task list.
The 3-Strike Protocol (Team Version)
STRIKE 1: Teammate diagnoses & fixes
→ Log error to team_findings.md
→ Try alternative approach
STRIKE 2: Teammate tries different method
→ Update team_findings.md with attempt
→ If still failing, message lead
STRIKE 3: Escalate to lead
→ Lead reviews team_findings.md
→ Lead may reassign or intervene
AFTER 3 STRIKES: Lead escalates to user
→ Explain team's attempts
→ Share specific blockers
→ Ask for guidance
Anti-Patterns
| Don't | Do Instead |
|---|---|
| Let teammates work in isolation | Require shared file updates |
| Give vague teammate instructions | Assign specific phases with clear deliverables |
| Skip the planning phase | Always create team_plan.md first |
| Have teammates edit same files | Assign file ownership to avoid conflicts |
| Run many teammates for simple tasks | Use single agent or subagents |
| Forget to clean up team | Always cleanup when done |
Templates
Copy these to start:
- templates/team_plan.md — Team phase tracking
- templates/team_findings.md — Shared discoveries
- templates/team_progress.md — Session logging
Scripts
scripts/check-team-complete.sh— Verify all phases completescripts/check-team-complete.ps1— Windows versionscripts/team-status.py— Get team status summary
Advanced Topics
- Manus Principles: See reference.md
- Real Examples: See examples.md
Cleanup
When finished, always clean up the team:
Clean up the team
This removes team resources. Shut down teammates first if any are still running.
