New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Workspace

by shadcn-labs in shadcn-labs/agentcn

How to safely operate the sandboxed workspace. An agent skill from shadcn-labs/agentcn.

MITAuto-check passed

Install Workspace

skills CLI
$ npx skills add shadcn-labs/agentcn --skill workspace -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shadcn-labs/agentcn workspace --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shadcn-labs/agentcn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/registry/flue/claw/skills/workspace .claude/skills/workspace && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
workspace
GitHub stars
490
Token cost
~141 tokens
SKILL.md length
65 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

How to safely operate the sandboxed workspace. An agent skill from shadcn-labs/agentcn.

  • Works in 6 steps: Plan the task as a short ordered… → Inspect first: read files or ls a… → Make the smallest change that advances… → …
  • Any multi-step task involving files
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Workspace is an agent skill from shadcn-labs/agentcn. How to safely operate the sandboxed workspace. Use for any multi-step task involving files or shell commands.

Its SKILL.md is about 140 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: shadcn/ui, but for building agents. 🤖. The licence is MIT.

When your agent uses it

  • Any multi-step task involving files

Example prompts

  • “/workspace”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  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.

What it can do on your machine

Read from SKILL.md and the folder at commit 4cd4d83. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Workspace loads about 141 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 65 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~141

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shadcn-labs/agentcn at commit 4cd4d83, republished under its MIT licence (© shadcn-labs). 65 words, ~141 tokens.

Download SKILL.mdSave it as .claude/skills/workspace/SKILL.md (or your agent's skills folder).
name
workspace
description
How to safely operate the sandboxed workspace. Use for any multi-step task involving files or shell commands.

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.

© shadcn-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in registry/flue/claw/skills/workspace of shadcn-labs/agentcn.

Open the folder on GitHubat commit 4cd4d83

Compare with similar skills

Workspace next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Workspace compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Workspace this skillshadcn-labs/agentcn490—~141Automated safety check: PassMIT
Agent Sandboxruvnet/ruflo74k2 repos~777Automated safety check: PassMIT
It Operationsdavila7/claude-code-templates33k1 repos~3.7kAutomated safety check: PassMIT
Sandbox Benchvercel/next.js143k—~4.1kAutomated safety check: PassMIT
Operator Approval Loopaffaan-m/ECC276k—~3.3kAutomated safety check: PassMIT
Sandboxalsk1992/CloddsBot3k—~341Automated safety check: PassMIT

Similar skills

  • Agent Sandbox

    ruvnet/ruflo

    Agent skill for sandbox - invoke with $agent-sandbox. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~777 tokens
    Auto-check passed

  • It Operations

    davila7/claude-code-templates

    Manages IT infrastructure, monitoring, incident response, and service reliability.

    33k GitHub starsUsed in 1 repo~3.7k tokens
    DevOps & CloudAuto-check passed

  • Sandbox Bench

    vercel/next.js

    Official

    Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app…

    143k GitHub stars~4.1k tokensUpdated today
    Data & AnalyticsAuto-check passed

  • Operator Approval Loop

    affaan-m/ECC

    Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.

    276k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Sandbox

    alsk1992/CloddsBot

    Visual HTML canvas sandbox for agent-driven UI and live previews

    3k GitHub stars~341 tokensUpdated 7 days ago
    Auto-check passed

  • Business Operations Skills

    alirezarezvani/claude-skills

    A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…

    28k GitHub stars~2.3k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

More from shadcn-labs/agentcn

  • Mastra File Agents

    shadcn-labs/agentcn

    Migrate Mastra code-based agents (agents built with new Agent(...) and registered in a Mastra({ agents }) map) to the file-based convention: one directory per agent under src/mastra/agents.

    490 GitHub stars~2.4k tokensUpdated 3 days ago
    Auto-check passed

  • Flue

    shadcn-labs/agentcn

    A skill your agent uses when building, debugging, reviewing, or documenting Flue agents, workflows, channels, skills, tools, sandboxes, targets, routing, persistence, observability, or CLI usage…

    490 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed

  • SEO Audit

    shadcn-labs/agentcn

    How to present the deterministic AI-SEO audit returned by auditpage.

    490 GitHub stars~598 tokensUpdated 3 days ago
    Auto-check passed

  • Research

    shadcn-labs/agentcn

    Iterative, self-evaluating web research. An agent skill from shadcn-labs/agentcn.

    490 GitHub stars~133 tokensUpdated 3 days ago
    Auto-check passed

Questions about Workspace

What does Workspace do?

How to safely operate the sandboxed workspace. An agent skill from shadcn-labs/agentcn. Workspace is an agent skill from shadcn-labs/agentcn. How to safely operate the sandboxed workspace.

When should I use Workspace?

Workspace fits situations like: any multi-step task involving files.

How do I install Workspace in Claude Code?

Run `npx skills add shadcn-labs/agentcn --skill workspace -a claude-code`. Or copy the skill folder (registry/flue/claw/skills/workspace in shadcn-labs/agentcn) into .claude/skills/workspace in your project. Claude Code loads it when a task matches its description.

How do I install Workspace in Codex?

Run `npx skills add shadcn-labs/agentcn --skill workspace -a codex`. Or copy the skill folder (registry/flue/claw/skills/workspace in shadcn-labs/agentcn) into .agents/skills/workspace in your project. Codex loads it when a task matches its description.

Can I use Workspace in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shadcn-labs/agentcn --skill workspace -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workspace, .gemini/skills/workspace, .github/skills/workspace and .opencode/skills/workspace in your project.

What does Workspace need to run?

SKILL.md names no scripts, command-line tools or credentials: Workspace is instructions for the agent only.

Does Workspace access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Workspace safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Workspace use?

Workspace is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Workspace use?

About 141 tokens (SKILL.md is roughly 564 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Workspace?

Skills that share tags, products or a category with Workspace: Agent Sandbox (ruvnet/ruflo, 74k stars), It Operations (davila7/claude-code-templates, 33k stars), Sandbox Bench (vercel/next.js, 143k stars) and Operator Approval Loop (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workspace?

shadcn-labs (a GitHub organization) maintains it in shadcn-labs/agentcn, which has 490 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

Source: shadcn-labs/agentcn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.