cloudflare-sandbox

cloudflare-sandbox is a skill for Claude Code from secondsky/claude-skills. It costs 40 tokens per session (4,181 once invoked), scanned A, original, MIT.

A Cloudflare SDK for running code inside isolated Linux containers at the network edge. It can execute untrusted programs and scripts, including Python and Node.js code.

In plain words
What is it for?
Use it to run user-submitted code, AI code interpreters, Python or Node.js scripts, and Git operations in Cloudflare-based applications.
Why use it?
It gives potentially unsafe code its own environment instead of running it directly alongside your application. This is useful for code interpreters and automated development tasks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the cloudflare-sandbox plugin — 1 skill shipped together

Good fit Use it to run user-submitted code, AI code interpreters, Python or Node.js scripts, and Git operations in Cloudflare-based applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/secondsky/claude-skills/cloudflare-sandbox
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add secondsky/claude-skills --skill cloudflare-sandbox
Clone the repo
git clone --depth 1 https://github.com/secondsky/claude-skills

Made for: Claude Code.

Or install cloudflare-sandbox, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cloudflare-sandbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/secondsky/claude-skills/cloudflare-sandbox/github.svg)](https://agentmods.dev/skills/secondsky/claude-skills/cloudflare-sandbox)
Your own site
<a href="https://agentmods.dev/skills/secondsky/claude-skills/cloudflare-sandbox"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/cloudflare-sandbox/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cloudflare-sandbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/secondsky/claude-skills/cloudflare-sandbox"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/cloudflare-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.04181
Opus 5.5 $0.00016 $0.01672
Sonnet 5.5 $0.00008 $0.00836
Haiku 4.5 $0.00004 $0.00418

Measured 1mo ago against content hash 267cd3ec1fd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cloudflare-sandbox scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/example-script.sh, scripts/setup-sandbox-binding.sh, scripts/test-sandbox.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

async fetch(request: Request, env: Env): Promise<Response> {
plugins/cloudflare-sandbox/skills/cloudflare-sandbox/SKILL.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cloudflare Sandboxes SDK

Status: Production Ready (Open Beta) Last Updated: 2025-12-10 Dependencies: cloudflare-worker-base, cloudflare-durable-objects (recommended for understanding) Latest Versions: @cloudflare/[email protected], Docker image: cloudflare/sandbox:0.6.3-python

⚠️ BREAKING CHANGE (v0.6.0): Python is no longer included in the default image. Use cloudflare/sandbox:<version>-python for Python support (~1.3GB with data science packages). The lean variant (~600-800MB) excludes Python.


Quick Start (15 Minutes)

1. Install SDK and Setup Wrangler

bun add @cloudflare/sandbox@latest  # preferred
# or: bun add @cloudflare/sandbox@latest

wrangler.jsonc:

{
  "name": "my-sandbox-worker",
  "main": "src/index.ts",
  "compatibility_flags": ["nodejs_compat"],
  "containers": [{
    "class_name": "Sandbox",
    "image": "cloudflare/sandbox:0.6.3-python",
    "instance_type": "lite"
  }],
  "durable_objects": {
    "bindings": [{
      "class_name": "Sandbox",
      "name": "Sandbox"
    }]
  },
  "migrations": [{
    "tag": "v1",
    "new_sqlite_classes": ["Sandbox"]
  }]
}

Why this matters:

  • nodejs_compat enables Node.js APIs required by SDK
  • containers defines the Ubuntu container image
  • durable_objects binding enables persistent routing
  • migrations registers the Sandbox class

2. Create Your First Sandbox Worker

import { getSandbox, type Sandbox } from '@cloudflare/sandbox';
export { Sandbox } from '@cloudflare/sandbox';

type Env = {
  Sandbox: DurableObjectNamespace<Sandbox>;
};

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    // Get sandbox instance (creates if doesn't exist)
    const sandbox = getSandbox(env.Sandbox, 'my-first-sandbox');

    // Execute Python code
    const result = await sandbox.exec('python3 -c "print(2 + 2)"');

    return Response.json({
      output: result.stdout,
      success: result.success,
      exitCode: result.exitCode
    });
  }
};

Read the full file on GitHub · 533 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 533 lines · 40 tokens per session scan A 267cd3ec1fd6

Subscribe to this mod's changes

cloudflare-sandbox is a skill published in the GitHub repository secondsky/claude-skills (236 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 4,181 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

decide

A reusable decision procedure, and a copyable prototype for the guard that encodes it — derive the population, set one threshold by what being wrong costs, name the offender, and break it once to prove it can fail. Use when writing a check, guard, gate or validation of any kind, or when deciding whether something is…

ArcticFox2029/chamnan · 93 tokens

remember

Record why something is the way it is — a decision and its reasoning, a lesson that cost time, or a standing constraint. Use when the reasoning behind a choice would be expensive to reconstruct later.

ArcticFox2029/chamnan · 40 tokens

bootstrap

Set up chamnan in this repository for the first time — build the architecture index, measure how well the code describes itself, fill in missing file comments, and record a baseline. Run once per repo.

ArcticFox2029/chamnan · 41 tokens

milestone

Record a change that reshaped the repository — what moved, why it was worth doing, and which areas it touched. Use after a migration, a rewrite, or a decision that changed how part of the system works.

ArcticFox2029/chamnan · 44 tokens

resume

Write down where this stretch of work stopped, so the next session continues instead of restarting. Use at the end of a working session, or when handing the repository to someone else.

ArcticFox2029/chamnan · 36 tokens

review

Review a change with what this repository knows about it — who depends on the file, which tests cover it, what broke here before, and what the repo has written down. Use before approving a diff, opening a PR, or when asked to review.

ArcticFox2029/chamnan · 51 tokens