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.
git clone --depth 1 https://github.com/henkisdabro/cloudflare-workers-react-boilerplateWrote 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.
[](https://agentmods.dev/commands/henkisdabro/cloudflare-workers-react-boilerplate/setup-sandbox)<a href="https://agentmods.dev/commands/henkisdabro/cloudflare-workers-react-boilerplate/setup-sandbox"><img src="https://agentmods.dev/badge/commands/henkisdabro/cloudflare-workers-react-boilerplate/setup-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.
<a href="https://agentmods.dev/commands/henkisdabro/cloudflare-workers-react-boilerplate/setup-sandbox"><img src="https://agentmods.dev/badge/commands/henkisdabro/cloudflare-workers-react-boilerplate/setup-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02604 |
| Opus 5.5 | $0.00000 | $0.01042 |
| Sonnet 5.5 | $0.00000 | $0.00521 |
| Haiku 4.5 | $0.00000 | $0.00260 |
Grade C, and why
setup-sandbox scanned grade C with 2 findings 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 24d ago.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
RUN apt-get update && apt-get install -y --no-install-recommends python3 && rm -rf /var/lib/apt/lists/* Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The base image has Node.js 24 but no Python, Git or curl. For the AI code execution option, add How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Cloudflare Sandbox
You are helping the user add Cloudflare Sandbox SDK 1.0 (@cloudflare/sandbox 1.0.0) to this
project for isolated code execution. The project is Vite + @cloudflare/vite-plugin, with the Worker
in worker/index.ts and config in wrangler.jsonc.
Base every step on the current docs rather than memory: https://developers.cloudflare.com/sandbox/ -
if anything below disagrees with them, the docs win. Sandbox SDK 0.x (getSandbox(),
"unsafe": { "bindings": [{ "type": "sandbox" }] }) is legacy until 2026-12-31; do not generate 0.x code.
What is Sandbox SDK 1.0?
A sandbox is a Durable Object the project defines plus the Linux container it starts, each in its own
microVM. The Durable Object drives the container through this.ctx.container (start(), exec(),
getTcpPort()); @cloudflare/sandbox adds the Files, S3Mount and DirectoryBackup helpers.
Full guide: SANDBOX.md.
Before Starting
Confirm with the user, and stop if any is missing:
- Workers Paid plan - Containers do not run on Free.
- Docker is running - check with
docker info. Bothpnpm devand deploys build the image. - The code really needs Linux - if it is JavaScript that only calls methods the Worker defines, suggest a Dynamic Worker instead.
Interactive Setup
Ask the user what they want to build:
- Run commands - execute shell commands or scripts from the Worker
- AI code execution - Claude writes Python, the sandbox runs it
- Something else - preview a web app, background processes, a browser terminal, R2 mounts, snapshots or coding agents. Do Steps 1-6, then follow the matching guide and example linked from cloudflare/sandbox-sdk.
Setup Steps
Step 1: Install the package
pnpm add -E @cloudflare/sandbox
Note the installed version - the Dockerfile tag in Step 2 must match it.
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.
- 24d ago Changed · -53 lines scan A → C 2304d53e9b28
- 1mo ago First seen · 340 lines · 0 tokens per session scan A 5d4000c8a4e5
setup-sandbox is a command published in the GitHub repository henkisdabro/cloudflare-workers-react-boilerplate (13 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,604 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
push-changes
If no topic provided, just document the recent changes. If a topic is provided, focus on documenting that topic.
create-PR
Command "create-PR" from bartstc/vite-ts-react-template, covering create a pr against this branch: $arguments, follow these steps and remember.
plugin-commands
:::info This document covers all build, test, and smoke commands for eIsland native plugins. Windows plugins live under plugins/windows/; macOS helpers live under plugins/macos/. Each plugin has its own package.json with independent scripts. ::.
e2e-testing
:::info The Playwright suite launches the real Electron main process and built React UI on Windows and macOS. It exercises the preload bridge, IPC handlers, and file storage. See Testing Commands for the separate Vitest suite. ::.
quality-commands
:::info This document covers all code quality commands for the eIsland project — ESLint, Stylelint, HTML validation, comment checks, and i18n completeness. ::.
esa-commands
:::info This document covers the ESA (Edge Security Acceleration) CDN cache purge commands for clearing cached content on Alibaba Cloud ESA. These commands use the official @alicloud/esa20240910 SDK. ::.