# Workspace

> How to safely operate the sandboxed workspace. Use for any multi-step task involving files or shell commands.

- Skill: `shadcn-labs/workspace-2` (Agent Skill)
- Install (CLI): `npx get-skill add shadcn-labs/workspace-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/shadcn-labs/workspace-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: shadcn-labs (https://skillmd.com/u/shadcn-labs)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/shadcn-labs/workspace-2

---


## Working in the Workspace

1. Plan the task as a short ordered checklist.
2. Inspect first: read files or `ls` a directory before changing anything.
3. Make the smallest change that advances the task; re-check after each step.
4. Keep every path inside the workspace.
5. Prefer reversible, non-destructive commands. Explain risky ones before running.
6. Finish by summarizing exactly what you created or changed.

