plan-manager（计划经理）

Plan Manager

Unified plan management system for coordinating OpenClaw Agent execution plans and Human task plans.

Overview

This skill provides a dual-track planning system:

Directory Structure

plans/
├── README.md                 # This file - overview and coordination guide
├── agent/
│   ├── plans-overview.md     # Agent's high-level execution board
│   ├── detailed/
│   │   ├── index.md          # Index of all detailed agent plans
│   │   └── XX-{plan-name}.md # Individual agent execution plans
│   └── archive/              # Completed agent plans
└── human/
    ├── plans-overview.md     # Human's high-level task board
    ├── detailed/
    │   ├── index.md          # Index of all detailed human plans
    │   └── XX-{plan-name}.md # Individual human task plans
    └── archive/              # Completed human plans

When to Use Which Track

Use Agent Track When:

• The OpenClaw Agent needs to execute multi-step tasks
• Tool sequences and execution workflows need documentation
• Tracking token usage and execution progress
• Breaking down complex user requests into actionable steps

Use Human Track When:

• The human user has personal tasks or todos
• Project milestones and deadlines need tracking
• Long-term goals and plans need organization
• Human decision points or approvals are required

Coordination Patterns

Pattern 1: Agent Assists Human Plan

Human creates a plan → Agent creates corresponding execution plan → Agent executes → Both update status

Example:

Human: "Plan a trip to Japan"
  ↓
human/plans-overview.md: "Plan Japan trip" (Status: In Progress)
  ↓
agent/plans-overview.md: "Research flights, hotels, itinerary" (Status: In Progress)
  ↓
[Agent executes research tasks]
  ↓
Both tracks updated to Done

Pattern 2: Agent Autonomous Execution

User requests complex task → Agent creates execution plan → Agent executes independently

Example:

User: "Refactor the auth module"
  ↓
agent/plans-overview.md: "Auth module refactor" (Status: In Progress)
  ↓
[Agent executes refactoring with detailed plan]
  ↓
Agent updates status to Done

Pattern 3: Human Oversight

Agent creates plan → Requests human approval → Human approves/modifies → Agent executes

Example:

User: "Design a new feature"
  ↓
agent/plans-overview.md: "Design new feature" (Status: Pending Approval)
  ↓
[Agent presents plan to human]
  ↓
human/plans-overview.md: "Review and approve feature design" (Status: In Progress)
  ↓
[Human reviews, approves]
  ↓
Agent proceeds to execution

Quick Start

For Agent Tasks:

1. Create plans/agent/plans-overview.md
2. Add execution items to the status table
3. Create plans/agent/detailed/XX-{plan-name}.md for complex tasks
4. Update plans/agent/detailed/index.md
5. Mark steps complete as execution progresses

For Human Tasks:

1. Create plans/human/plans-overview.md
2. Add task items to the status table
3. Create plans/human/detailed/XX-{plan-name}.md for complex tasks
4. Update plans/human/detailed/index.md
5. Update statuses weekly or as tasks complete

Templates

Templates are organized by track:

templates/
├── agent/           # Templates for Agent plans
│   ├── plans-overview.md
│   ├── detailed-plan.md
│   └── index.md
└── human/           # Templates for Human plans
    ├── plans-overview.md
    ├── detailed-plan.md
    └── index.md

Status Values

Tips

• Prefix plan IDs: Use A-1, A-2 for agent plans and H-1, H-2 for human plans when cross-referencing
• Link related plans: In the Notes column, reference related plans from the other track
• Archive completed plans: Move completed plans to the archive/ folder monthly
• Review weekly: Check both tracks weekly to ensure coordination
• Use consistent naming: kebab-case for all filenames (01-auth-refactor.md)

Example: Coordinated Web Development Project

Human Track (plans/human/plans-overview.md):

| H-1 ||***|| Launch new website ||***|| In Progress ||***|| High ||***|| Q2 2025 ||***|| June 30 ||***|| A-1, A-2 |

Agent Track (plans/agent/plans-overview.md):

| A-1 ||***|| Design database schema ||***|| Done ||***|| High ||***|| Week 1 ||***|| - ||***|| For H-1 |
| A-2 ||***|| Implement API endpoints ||***|| In Progress ||***|| High ||***|| Week 2-3 ||***|| - ||***|| For H-1 |

This structure ensures both human goals and agent execution are visible and coordinated.