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.
npx agentmods add skills/alsk1992/cloddsbot/sandboxnpx skills add alsk1992/CloddsBot --skill sandboxgit clone --depth 1 https://github.com/alsk1992/CloddsBotWrote 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/skills/alsk1992/cloddsbot/sandbox)<a href="https://agentmods.dev/skills/alsk1992/cloddsbot/sandbox"><img src="https://agentmods.dev/badge/skills/alsk1992/cloddsbot/sandbox.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00324 |
| Opus 5 | $0.00006 | $0.00162 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
sandbox 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 yesterday.
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.
What it actually says
Sandbox - Visual Canvas
Push HTML content to a live-updating canvas server for visual previews, dashboards, and agent-driven UI.
Commands
/sandbox start - Start the canvas server (returns URL)
/sandbox push <html> - Push HTML content to the canvas
/sandbox reset - Reset canvas to blank state
/sandbox screenshot - Take a screenshot of the current canvas
/sandbox status - Show canvas server status and settings
Environment Variables
| Variable | Description |
|---|---|
CANVAS_ALLOW_JS_EVAL |
Enable JavaScript evaluation in canvas (default: false) |
ALLOW_UNSAFE_SANDBOX |
Enable unsafe sandbox mode (default: false) |
Examples
/sandbox start
/sandbox push <h1>Hello World</h1><p>Live preview</p>
/sandbox screenshot
/sandbox status
/sandbox reset
How It Works
/sandbox startlaunches a local HTTP server that serves the canvas page/sandbox push <html>sends HTML to the canvas, rendered in real time/sandbox screenshotcaptures the current canvas state as an image/sandbox resetclears all HTML, CSS, and JS from the canvas/sandbox statusshows whether the server is running, the URL, and content sizes
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 47 lines · 13 tokens per session scan A 3b580d9e295c
sandbox is a skill published in the GitHub repository alsk1992/CloddsBot (872 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 324 once invoked, about $0.0001 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.
Other skills, from other repositories
agent-uat
AI 에이전트가 마크다운 시나리오를 읽고 사용자와 인터랙티브하게 실행하여 WAIaaS 기능을 메인넷/테스트넷에서 검증하는 시스템이다.
hive-market-research
Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…
hive-query
Default entry point for any live crypto question when Hive MCP is connected — prices, wallets, tokens, DeFi, NFTs, Solana, security, markets, DEX, networks, prediction markets. Use it whenever the answer depends on live or on-chain data instead of answering from memory, even if the user never mentions Hive. Routes…
hive-nft-research
Use this skill when the user asks about NFT collections or assets on EVM chains — ownership, metadata, traits, floor prices, sales, rarity, spam/authenticity checks — like "what's the floor on this collection", "who owns this NFT", "is this collection spam". Use it whenever the user needs current NFT evidence rather…
hive-prediction-markets
Use this skill when the user asks about prediction markets — Polymarket or Kalshi events, markets, outcomes, odds, prices, liquidity, stats, traders, holders, or trades — including "what are the odds of X", "find markets about Y", or comparing venues. Use it whenever live prediction-market evidence is needed. Never…
hive-wallet-investigation
Use this skill whenever the user wants to look inside a wallet or address — portfolio, holdings, balances, transfers, PnL, NFT exposure, DeFi positions, whale moves, "what does this address hold", "trace this wallet's activity" — even if they just paste an address. Requires wallet address and chain before executing…