sandbox-internet-handler

sandbox-internet-handler is a skill for Claude Code, Codex from Stijnman/grok-custom-skills. It costs 37 tokens per session (300 once invoked), scanned A, original, MIT.

A read-only web-fetching tool that retrieves text from HTTPS web pages in a restricted environment.

In plain words
What is it for?
Use it to safely fetch a URL, return readable text or Markdown, enforce limits, and flag suspicious content.
Why use it?
It lets an agent inspect online content while blocking scripts and embedded code from running.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to safely fetch a URL, return readable text or Markdown, enforce limits, and flag suspicious content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stijnman/grok-custom-skills/sandbox-internet-handler
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 Stijnman/grok-custom-skills --skill sandbox-internet-handler
Clone the repo
git clone --depth 1 https://github.com/Stijnman/grok-custom-skills

Made for: Claude Code, Codex.

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 sandbox-internet-handler

README.md
[![agentmods](https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/sandbox-internet-handler/github.svg)](https://agentmods.dev/skills/stijnman/grok-custom-skills/sandbox-internet-handler)
Your own site
<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/sandbox-internet-handler"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/sandbox-internet-handler/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 sandbox-internet-handler

Your own site · 80×15
<a href="https://agentmods.dev/skills/stijnman/grok-custom-skills/sandbox-internet-handler"><img src="https://agentmods.dev/badge/skills/stijnman/grok-custom-skills/sandbox-internet-handler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 300 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00037 $0.00300
Opus 5 $0.00018 $0.00150
Sonnet 5 $0.00007 $0.00060
Haiku 4.5 $0.00004 $0.00030

Measured 9d ago against content hash 265a08971111, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sandbox-internet-handler scanned grade A with 0 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.grok/skills/sandbox-internet-handler/SKILL.md · 47 lines

What it actually says

Sandbox Internet Handler

When to Use

  • User says sandbox fetch or task matches this capability
  • User says safe web access or task matches this capability
  • User says fetch URL safely or task matches this capability

Workflow

  1. Validate URL scheme (https only).
  2. Fetch with timeout and size limit.
  3. Strip scripts; return text/markdown only.
  4. Flag suspicious content; do not execute embedded code.

Integrations

  • internet-enabler
  • web-scraper
  • privacy-redactor

Error Handling

Failure Response
Timeout Report partial content or suggest alternate source.

Gotchas

  • Never pass fetched HTML to exec or eval.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

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. 9d ago First seen · 47 lines · 37 tokens per session scan A 265a08971111

Subscribe to this mod's changes

sandbox-internet-handler is a skill published in the GitHub repository Stijnman/grok-custom-skills (9 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 300 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. 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

agent-browser

Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.

superagent-ai/grok-cli · 31 tokens

wechat-article-video-download

Download a specified video from a public WeChat Official Account article and verify the saved MP4. Use when the user provides an mp.weixin.qq.com article URL and asks to save, extract, grab, or download the first or Nth embedded article video. Do not use for Channels livestreams, login-only media, DRM, encrypted…

LearnPrompt/carl-skills · 81 tokens

control-ui

Drive and inspect a local web, IDE, or Electron UI with browser or CDP automation and evidence. Use for UI regressions, screenshots, accessibility snapshots, visual diffs, focus, keyboard, scrolling, resize, console, network, performance, or heap checks. Do not use for backend-only changes or for a screenshot without…

AnastasiyaW/codex-claude-code-config · 73 tokens

takomi-flow

Use when Codex needs to operate Google Flow as a reusable agent tool through safe browser automation: bootstrap/login a persistent Flow profile, smoke-check access without spending credits, prepare image or video generation request files, run guarded Flow generations, download assets, inspect results, or integrate…

J-StaR-Films-Studios/VibeCode-Protocol-Suite · 93 tokens

high-fidelity-extraction

Advanced protocol for extracting granular social media and web intelligence using browser automation and DOM analysis.

J-StaR-Films-Studios/VibeCode-Protocol-Suite · 23 tokens

goal-meta-skill

A guide for turning an unclear or complex task into a reviewable /goal instruction for coding agents.

bahayonghang/my-ai-cli-toolkit · 190 tokens