Agent skill

Cloud Sandbox

by dxos in dxos/dxos

Working inside the Claude Code cloud sandbox (Claude Code on the web, remote sessions, scheduled runs).

Custom licenceAuto-check passedTesting & QA

Install Cloud Sandbox

skills CLI
$ npx skills add dxos/dxos --skill cloud-sandbox -a claude-code

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

GitHub CLI
$ gh skill install dxos/dxos cloud-sandbox --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/dxos/dxos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cloud-sandbox .claude/skills/cloud-sandbox && 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
cloud-sandbox
GitHub stars
525
Token cost
~3.9k tokens
SKILL.md length
1,847 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
Custom licence

At a glance

Working inside the Claude Code cloud sandbox (Claude Code on the web, remote sessions, scheduled runs).

  • CLAUDECODEREMOTE is set
  • SKILL.md covers Detect it, Project hooks run; plugins do…, Tooling not on PATH and Nothing is prebuilt, and…, plus 3 more sections
  • Calls git, pnpm and gh; reaches dxos.network
  • Oxfmt are command not found

What it does

Cloud Sandbox is an agent skill from dxos/dxos. Working inside the Claude Code cloud sandbox (Claude Code on the web, remote sessions, scheduled runs). Use when CLAUDECODEREMOTE is set; when moon, gh, or oxfmt are "command not found"; when Chromium or Playwright fails with ERRCONNECTIONRESET or a TLS error against an HTTPS host that curl reaches fine; when /dxos:project answers Unknown command or a plugin's skills are missing from the session; or when a build or dev server unexpectedly triggers a full pnpm install.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Browser testing. It works with Playwright and pnpm. The repository describes itself as: TypeScript implementation of the DXOS protocols, SDK, toolchain and Composer.

When your agent uses it

  • CLAUDECODEREMOTE is set
  • Oxfmt are command not found
  • Playwright fails with ERRCONNECTIONRESET
  • A TLS error against an HTTPS host that curl reaches fine

Example prompts

  • “command not found”
  • “/cloud-sandbox”

What it can do on your machine

Read from SKILL.md and the folder at commit f0fc12a. 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

    Shell commands in SKILL.md call:

    • git
    • pnpm
    • gh
    • playwright
    • bash
    • claude
    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • dxos.network

    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

Cloud Sandbox loads about 3.9k tokens when it runs. Until then it costs about 125 tokens; SKILL.md has 1,847 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,847 words (~3,949 tokens).

“The sandbox is an ephemeral Linux container running the agent against a fresh clone at /home/user/. It is not the environment AGENTS.md and .claude/CLAUDE.md assume, and several of their instructions do not hold here.”

— opening of SKILL.md by dxos, Custom licence
name
cloud-sandbox

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/cloud-sandbox of dxos/dxos.

Open the folder on GitHubat commit f0fc12a

Compare with similar skills

Cloud Sandbox 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.

Cloud Sandbox compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cloud Sandbox this skilldxos/dxos525—~3.9kAutomated safety check: PassCustom licence
Ckeditor5 TestingTriliumNext/Trilium38k—~3.3kAutomated safety check: PassAGPL-3.0
Agent Integration ReplayComfy-Org/ComfyUI_frontend2.1k—~805Automated safety check: NotesGPL-3.0
UI Previewtingly-dev/tingly-box351—~2kAutomated safety check: NotesMPL-2.0
Tuistoryremorses/tuistory366—~2.4kAutomated safety check: PassNone
E2E VerificationChorus-AIDLC/Chorus1.2k—~1.5kAutomated safety check: NotesAGPL-3.0

Similar skills

  • Ckeditor5 Testing

    TriliumNext/Trilium

    Testing CKEditor 5 plugins in the Trilium monorepo. An agent skill from TriliumNext/Trilium.

    38k GitHub stars~3.3k tokensUpdated today
    Testing & QAAuto-check passed
  • Agent Integration Replay

    Comfy-Org/ComfyUI_frontend

    Replay recorded agent conversations as Playwright tests against the real chat panel and canvas.

    2.1k GitHub stars~805 tokensUpdated today
    Testing & QAAuto-check: notes
  • UI Preview

    tingly-dev/tingly-box

    Capture headless-Chrome screenshots of the tingly-box frontend (running locally in mock mode) so frontend changes can be visually verified in environments without a real browser.

    351 GitHub stars~2k tokensUpdated today
    Testing & QAAuto-check: notes
  • Tuistory

    remorses/tuistory

    tmux for AI agents. An agent skill from remorses/tuistory.

    366 GitHub stars~2.4k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • E2E Verification

    Chorus-AIDLC/Chorus

    A skill your agent uses when manually verifying a Chorus frontend change in a real browser — finding local login credentials, driving the running dev server with the Playwright MCP, logging in…

    1.2k GitHub stars~1.5k tokensUpdated yesterday
    Testing & QAAuto-check: notes
  • E2E Playwright

    Asvarox/allkaraoke

    Run, write, and debug Playwright E2E tests for this project.

    261 GitHub stars~876 tokensUpdated today
    Testing & QAAuto-check passed

More from dxos/dxos

All 41 skills in this repo
  • Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…

    525 GitHub stars~4.4k tokensUpdated today
    Auto-check passed
  • Forensically inspect and repair Composer browser profiles — offline (Chrome OPFS / SQLite extract) or live via /recovery.html debug port.

    525 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Migrate Oxfmt

    dxos/dxos

    Guide for migrating a project from Prettier or Biome to Oxfmt.

    525 GitHub starsUsed in 3 repos~2.2k tokens
    Auto-check passed
  • Moon

    dxos/dxos

    This skill should be used when the user asks to "configure moon", "set up moonrepo", "create moon tasks", "run moon commands", "configure moon workspace", "add moon project", "moon ci setup", "moon…

    525 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Reference for SubductionPolicy (the four hooks authorizeConnect, authorizeFetch, authorizePut, filterAuthorizedFetch passed via Subduction.hydrate(..., policy) or new Repo({ subductionPolicy })).

    525 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Autocue

    dxos/dxos

    Record a demo of the running app that the agent drives itself — a .mdl QA test or an ad-hoc walkthrough — as a captioned .webm (or a screenshot), trimmed of dead air and ready to attach.

    525 GitHub stars~12k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Cloud Sandbox

What does Cloud Sandbox do?

Working inside the Claude Code cloud sandbox (Claude Code on the web, remote sessions, scheduled runs). Cloud Sandbox is an agent skill from dxos/dxos. Working inside the Claude Code cloud sandbox (Claude Code on the web, remote sessions, scheduled runs).

When should I use Cloud Sandbox?

Cloud Sandbox fits situations like: CLAUDECODEREMOTE is set; oxfmt are command not found; playwright fails with ERRCONNECTIONRESET; A TLS error against an HTTPS host that curl reaches fine.

How do I install Cloud Sandbox in Claude Code?

Run `npx skills add dxos/dxos --skill cloud-sandbox -a claude-code`. Or copy the skill folder (.agents/skills/cloud-sandbox in dxos/dxos) into .claude/skills/cloud-sandbox in your project. Claude Code loads it when a task matches its description.

How do I install Cloud Sandbox in Codex?

Run `npx skills add dxos/dxos --skill cloud-sandbox -a codex`. Or copy the skill folder (.agents/skills/cloud-sandbox in dxos/dxos) into .agents/skills/cloud-sandbox in your project. Codex loads it when a task matches its description.

Can I use Cloud Sandbox 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 dxos/dxos --skill cloud-sandbox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cloud-sandbox, .gemini/skills/cloud-sandbox, .github/skills/cloud-sandbox and .opencode/skills/cloud-sandbox in your project.

What does Cloud Sandbox need to run?

Going by SKILL.md and its folder, Cloud Sandbox needs the command-line tools its instructions call (git, pnpm, gh, playwright, bash and claude).

Does Cloud Sandbox access the network?

SKILL.md names 1 domain. In commands or code: dxos.network; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Cloud Sandbox 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 Cloud Sandbox use?

Cloud Sandbox has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Cloud Sandbox use?

About 3.9k tokens (SKILL.md is roughly 16k 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 Cloud Sandbox?

Skills that share tags, products or a category with Cloud Sandbox: Ckeditor5 Testing (TriliumNext/Trilium, 38k stars), Agent Integration Replay (Comfy-Org/ComfyUI_frontend, 2.1k stars), UI Preview (tingly-dev/tingly-box, 351 stars) and Tuistory (remorses/tuistory, 366 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cloud Sandbox?

dxos (a GitHub organization) maintains it in dxos/dxos, which has 525 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 8, 2026.

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