Planner

Local-first planning engine for trips, weeks, launches, projects, schedules, and structured decision-making. Use whenever the user wants to plan something, o...

Security Scan

The skill is internally consistent with its description: it is a small, local-first Python-based planner that reads/writes JSON under ~/.openclaw/workspace and does not request external credentials, network access, or unusual system privileges.

Purpose & Capability

Name/description (local-first planning) matches the included scripts: add/suggest/update/daily/weekly map and storage utilities. The code only implements plan capture, ranking, and local JSON storage — appropriate for the stated purpose.

Instruction Scope

SKILL.md and the scripts limit activity to local storage and CLI operations. The runtime instructions require python3 and state storage paths; no instructions ask the agent to read unrelated files, environment variables, or call external services.

Install Mechanism

There is no install spec (instruction-only skill) and the included code is plain Python with only standard-library imports. No downloads, external package installs, or archive extraction are requested.

Credentials

The skill requires no environment variables or credentials. The only filesystem access is to create/read/write ~/.openclaw/workspace/memory/planner/{plans.json,archive.json}, which is proportionate to a local planner.

Persistence & Privilege

always is false and the skill does not request persistent platform-level privileges or modify other skills. It creates and manages its own local storage only.

Assessment

This skill appears safe and does what it claims: store and manage plans locally under ~/.openclaw/workspace/memory/planner. Before installing, ensure you’re comfortable with plan data being stored in your home directory (consider file permissions or encrypting sensitive content). Verify python3 is available. If you have sensitive secrets, do not place them in plan fields. If you want extra assurance, review the included Python files yourself or run them in an isolated environment (container/VM) before enabling the skill for autonomous agent use.

Planner: Turn uncertainty into a workable plan.

Core Philosophy

1. Plans should reduce uncertainty, not create overhead.
2. Start with constraints, then shape the plan.
3. Large plans should become phases, milestones, and next steps.
4. Good planning creates clarity before execution begins.

Runtime Requirements

• Python 3 must be available as python3
• No external packages required

Storage

All data is stored locally only under:

• ~/.openclaw/workspace/memory/planner/plans.json
• ~/.openclaw/workspace/memory/planner/archive.json

No external sync. No cloud storage. No third-party planning APIs.

Plan Types

• trip: Travel, itinerary, booking sequence, budget-aware planning.
• week: Weekly structure, focus themes, time blocks, priorities.
• project: Multi-phase roadmap with milestones.
• launch: Rollout, preparation, dependencies, timeline.
• decision: Option comparison with constraints and tradeoffs.

Core Fields

• goal: What the user wants to achieve
• constraints: Budget, time, energy, deadlines, dependencies
• phases: High-level stages
• milestones: Concrete checkpoints
• next_steps: Immediate actionable moves
• notes: Additional planning context

Key Workflows

• Capture a plan: add_plan.py
• See best structure: suggest_plan.py
• Update a plan: update_plan.py
• Summarize today's planning view: daily_plan.py
• Review all active plans: weekly_map.py

Scripts

Script	Purpose
init_storage.py	Initialize local storage files
add_plan.py	Capture a new plan
suggest_plan.py	Show the best current plan or next phase
update_plan.py	Update plan status, dates, notes, or phases
daily_plan.py	Show active plans and immediate next steps
weekly_map.py	Review all plans across horizons