run-in-sandbox

Name: run-in-sandbox
Author: breadboard-ai

Skill by breadboard-ai · updated 22 days ago · ★ 423

Score 72

Teaches you how to properly operate in the sandboxed environment you're in. run-in-sandbox is published by breadboard-ai on GitHub.

Install GitHub

Yours? Claim it

Works withClaude CodeClaude apps Antigravity CLI

Maintenance

Last commit 22 days ago

Licence

Apache-2.0: permissive, fine for commercial use

Quality

Clear description, installs from GitHub, 423 stars, original repository

Security

No risky patterns in the files we checked

Install run-in-sandbox

Built from the published package, never by AI

git clone --depth 1 https://github.com/breadboard-ai/breadboard /tmp/breadboard && mkdir -p ~/.claude/skills && cp -r /tmp/breadboard/hives/antigravity/skills/run-in-sandbox ~/.claude/skills/run-in-sandbox

Run in your terminal. Claude Code loads skills from ~/.claude/skills automatically.

Step-by-step: install run-in-sandbox in Claude Code

git clone --depth 1 https://github.com/breadboard-ai/breadboard /tmp/breadboard && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/breadboard/hives/antigravity/skills/run-in-sandbox ~/.gemini/antigravity-cli/skills/run-in-sandbox

Antigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.

Step-by-step: install run-in-sandbox in Antigravity CLI

Skills can run scripts on your machine. Some need an API key: check the README.

Weekly newsletter

Like run-in-sandbox? Get the best new skills every week

The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.

Security check

No download-and-run commands, hidden instructions or signs of sending keys out were found.

Checked automatically: hives/antigravity/skills/run-in-sandbox/SKILL.md. This looks for known risky patterns and is not a full audit. How grades work

Inside the skill

Allowed tools: sandbox.*

SKILL.md498 B

Alternatives to run-in-sandbox

All alternatives →

frontend-api-contractsOpenHands

This skill should be used when the user asks to "add an API call", "change a backend", "update settings persistence", "change conversation events", "fix backend auth", "add Agent Server support", or changes src/api, backend registry, Cloud/runtime transport, settings, secrets, compatibility, or conversation resume behavior.

AAA Skill 91k

datachain-coredatachain-ai

Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.

AAA Skill 2.8k

limerickgenkit-ai

Respond as a single limerick. Use for playful or comic answers, or when the user asks for a limerick.

AAA Skill 6.5k

project-structuremicrosoft

Explains the project structure of the agent-framework .NET solution

AAA Skill 14k

fal-platformsickn33

Platform APIs for model management, pricing, and usage tracking

AAA Skill 48k

gsd-reviewopen-gsd

Request cross-AI peer review of phase plans from external AI CLIs

AAA Skill 11k

run-in-sandbox vs frontend-api-contracts run-in-sandbox vs datachain-core run-in-sandbox vs limerick

run-in-sandbox: common questions

How do I install run-in-sandbox?

Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.

Is run-in-sandbox free?

The code is published under the Apache-2.0 licence. The service it connects to may have its own pricing.

Is run-in-sandbox safe to use?

It scores 72 of 100. Grades: maintenance A, licence A, quality B. Security check: grade A, no risky patterns found in the files checked. Review the code before you install. How grades work.

What are alternatives to run-in-sandbox?