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 skills add claude-office-skills/claude-office-plugin --skill sandbox-executorgit clone --depth 1 https://github.com/claude-office-skills/claude-office-pluginWrote 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/claude-office-skills/claude-office-plugin/sandbox-executor)<a href="https://agentmods.dev/skills/claude-office-skills/claude-office-plugin/sandbox-executor"><img src="https://agentmods.dev/badge/skills/claude-office-skills/claude-office-plugin/sandbox-executor/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/skills/claude-office-skills/claude-office-plugin/sandbox-executor"><img src="https://agentmods.dev/badge/skills/claude-office-skills/claude-office-plugin/sandbox-executor.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 | $0.00027 | $0.01124 |
| Opus 5 | $0.00014 | $0.00562 |
| Sonnet 5 | $0.00005 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade C, and why
sandbox-executor scanned grade C with 3 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 11d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://api.exchangerate-api.com/v4/latest/USD" | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
keywords: [python, pip, 爬虫, 抓取, scrape, crawl, 脚本, script, 下载, 安装, shell, bash, 命令行, terminal, 终端, pandas, numpy, requests, beautifulsoup, selenium, playwright, google play, app store, 评论, reviews, 数据采集, 数据抓取, 网页抓取, api调 Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
4. **pip 依赖声明在 options 中**:不要在 Python 代码里写 `os.system("pip install ...")` How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
沙盒执行器
当任务需要 Python 或 Shell 脚本(如安装第三方库、调用外部 API、网页抓取),使用 sandboxExec() 在安全沙盒中执行。
核心函数
var result = sandboxExec(language, code, options);
| 参数 | 类型 | 说明 |
|---|---|---|
| language | string | "python" 或 "shell" |
| code | string | 要执行的代码 |
| options.pip | string[] | Python 依赖包列表(可选) |
| options.timeout | number | 超时秒数,默认 60,最大 120 |
返回值
{
"ok": true,
"stdout": "脚本输出内容",
"stderr": "错误信息(如有)",
"exitCode": 0,
"timedOut": false
}
使用模式
核心原则:sandboxExec 获取数据 → WPS JavaScript 写入表格
// 第一步:在沙盒中用 Python 获取数据
var result = sandboxExec("python", `
import json
from google_play_scraper import reviews, Sort
result, _ = reviews(
'com.example.app',
lang='zh',
country='cn',
sort=Sort.NEWEST,
count=50
)
print(json.dumps(result, ensure_ascii=False, default=str))
`, { pip: ["google-play-scraper"], timeout: 90 });
if (!result.ok) return "Python 执行失败: " + result.error;
// 第二步:解析数据并写入表格
var data = JSON.parse(result.stdout);
var ws = Application.ActiveSheet;
ws.Range("A1").Value2 = "用户名";
ws.Range("B1").Value2 = "评分";
ws.Range("C1").Value2 = "评论";
ws.Range("D1").Value2 = "日期";
for (var i = 0; i < data.length; i++) {
var row = i + 2;
ws.Range("A" + row).Value2 = data[i].userName || "";
ws.Range("B" + row).Value2 = data[i].score || 0;
ws.Range("C" + row).Value2 = (data[i].content || "").substring(0, 200);
ws.Range("D" + row).Value2 = data[i].at || "";
}
return "已写入 " + data.length + " 条评论数据";
常见场景
网页数据抓取
var result = sandboxExec("python", `
import json, urllib.request
url = "https://api.example.com/data"
resp = urllib.request.urlopen(url)
data = json.loads(resp.read())
print(json.dumps(data))
`, { timeout: 30 });
使用第三方 Python 库
var result = sandboxExec("python", `
import json, pandas as pd
df = pd.read_csv("https://example.com/data.csv")
print(df.to_json(orient="records", force_ascii=False))
`, { pip: ["pandas"], timeout: 60 });
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.
- 11d ago First seen · 130 lines · 27 tokens per session scan C c2c289e0303b
sandbox-executor is a skill published in the GitHub repository claude-office-skills/claude-office-plugin (9 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,124 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…