plan — community agent-sandbox, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0

About this Skill

Secure local dev environment for AI agent collaboration

mattolson mattolson
[163]
[15]
Updated: 4/14/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 1/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Locale and body language aligned
Review Score
1/11
Quality Score
44
Canonical Locale
en
Detected Body Locale
en

Secure local dev environment for AI agent collaboration

Core Value

Secure local dev environment for AI agent collaboration

Ideal Agent Persona

Suitable for operator workflows that need explicit guardrails before installation and execution.

Capabilities Granted for plan

! Prerequisites & Limits

Why this page is reference-only

  • - The page lacks a strong recommendation layer.
  • - The page lacks concrete use-case guidance.
  • - The page lacks explicit limitations or caution signals.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is plan?

Secure local dev environment for AI agent collaboration

How do I install plan?

Run the command: npx killer-skills add mattolson/agent-sandbox. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

Which IDEs are compatible with plan?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add mattolson/agent-sandbox. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use plan immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

plan

Install plan, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Planning System

This is a three-tier planning system for iterative project development. Each tier produces artifacts that inform the next.

The Three Tiers

Tier 1: Project Planning

High-level planning done once at project start. Defines goals, approach, architecture, and milestones.

  • Output: docs/plan/project.md
  • Produces: List of milestones with identifiers (e.g., m1-auth, m2-dashboard)

Tier 2: Milestone Planning

Done at the start of each milestone. Breaks the milestone into discrete tasks.

  • Input: Project plan
  • Output: docs/plan/milestones/{milestone}/milestone.md
  • Produces: List of tasks with identifiers (e.g., m1.1-login-form, m1.2-signup-flow)

Tier 3: Task Planning

Done at the start of each task. Plans implementation, tracks execution, captures learnings.

  • Input: Milestone plan + accumulated learnings
  • Output: docs/plan/milestones/{milestone}/tasks/{task}/task.md
  • Also appends to: docs/plan/learnings.md

Naming Convention

  • Milestones: m{number}-{name} (e.g., m1-auth, m2-dashboard)
  • Tasks: m{milestone}.{task}-{name} (e.g., m1.1-login-form, m1.2-signup-flow)

File Structure

docs/plan/
├── project.md              # Tier 1 output - goals, architecture, milestones
├── learnings.md            # Accumulated learnings from all tasks
├── decisions/
│   ├── 001-switch-to-graphql.md
│   └── 002-defer-analytics.md
└── milestones/
    ├── m1-auth/
    │   ├── milestone.md    # Tier 2 output - milestone plan and task list
    │   ├── {milestone-level artifacts}
    │   └── tasks/
    │       ├── m1.1-login-form/
    │       │   ├── task.md
    │       │   └── {task artifacts}
    │       └── m1.2-signup-flow/
    │           └── task.md
    └── m2-dashboard/
        ├── milestone.md
        └── tasks/
            └── m2.1-user-profile/
                └── task.md

Learnings and Decisions

Planning is imperfect. As work progresses, we discover things we didn't anticipate and make decisions that change the plan.

Learnings

Lessons learned during execution that inform future planning. Captured in docs/plan/learnings.md. These may be technical or process-related.

Technical examples:

  • "API rate limits are lower than documented, need to batch requests"
  • "Integration tests take 5 minutes, run selectively during development"
  • "The auth library doesn't support refresh tokens out of the box"

Process examples:

  • "Breaking tasks into half-day chunks improved estimation accuracy"
  • "Spiking unfamiliar APIs before planning saved rework"
  • "Pairing on complex integrations caught issues earlier"

Learnings are reviewed at the start of each planning session.

Decisions

Significant changes to the plan, recorded as individual documents in docs/plan/decisions/.

When a decision changes the plan:

  1. Update the affected plan document (project.md, milestone.md) to reflect current state
  2. Create a decision record documenting the change and rationale

Decision document format:

markdown
1# {Number}: {Title} 2 3## Status 4 5{Proposed | Accepted | Superseded by XXX} 6 7## Context 8 9{What situation prompted this decision?} 10 11## Decision 12 13{What are we changing?} 14 15## Rationale 16 17{Why this approach over alternatives?} 18 19## Consequences 20 21{What changes as a result? What are the tradeoffs?}

Decisions are numbered sequentially: 001-switch-to-graphql.md, 002-defer-analytics.md.

Workflow

This is a conversational process. Describe your intent and I will:

  1. Identify which planning tier applies
  2. Look up relevant identifiers from existing plans
  3. Guide you through the appropriate planning process

Examples:

  • "Let's plan a new project" → Tier 1 project planning
  • "Let's start the auth milestone" → I look up the milestone in project.md, begin tier 2 planning
  • "Ready to work on login" → I find the task in the milestone plan, begin tier 3 planning

Learnings from each completed task feed into future task planning. When discoveries require plan changes, we update the plan and record a decision.

Getting Started

Describe what you want to work on:

  • Starting a new initiative? We'll do project planning.
  • Ready to begin a milestone? Tell me which one.
  • Ready to implement a task? Tell me what you're building.

Related Skills

Looking for an alternative to plan or another community skill for your workflow? Explore these related open-source skills.

View All

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

149.6k
0
AI

flags

Logo of vercel
vercel

The React Framework

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Developer