# Plan

> Build or update a task plan when a request has multiple sequential steps; use when the user asks to plan or when a task is large enough that order and verification matter.

- **Type:** Skill
- **Install:** `agentstack add skill-gizclaw-opencraft-plan`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [GizClaw](https://agentstack.voostack.com/s/gizclaw)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [GizClaw](https://github.com/GizClaw)
- **Source:** https://github.com/GizClaw/opencraft/tree/main/internal/capabilities/skills/assets/skills/plan

## Install

```sh
agentstack add skill-gizclaw-opencraft-plan
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Plan

When activated, turn the request into a concrete checklist before executing:

1. Break the request into steps small enough to verify one at a time; each step needs a clear outcome.
2. Submit the checklist with `update_plan`, keeping at most one step in_progress.
3. Update statuses as work progresses; a finished plan must not be re-submitted as pending.

Keep the plan visible to the user: it is the shared TODO list for the task.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [GizClaw](https://github.com/GizClaw)
- **Source:** [GizClaw/opencraft](https://github.com/GizClaw/opencraft)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-gizclaw-opencraft-plan
- Seller: https://agentstack.voostack.com/s/gizclaw
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.