google-workspace

google-workspace is a skill for Claude Code, Codex from malue-ai/dazee-small. It costs 32 tokens per session (1,156 once invoked), scanned A, original, MIT.

A Google Workspace integration for Calendar, Gmail, Drive, and Docs using Google’s MCP server. Google Workspace is Google’s collection of email, calendar, file-storage, and document tools.

In plain words
What is it for?
Use it to manage calendar events, search and handle email, find or upload Drive files, share files, and work with Google Docs.
Why use it?
It brings common work across those Google services into agent requests and supports OAuth2 sign-in so access can be authorized through Google.

Skill for Claude CodeCodex

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

Good fit Use it to manage calendar events, search and handle email, find or upload Drive files, share files, and work with Google Docs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/malue-ai/dazee-small/google-workspace
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 malue-ai/dazee-small --skill google-workspace
Clone the repo
git clone --depth 1 https://github.com/malue-ai/dazee-small

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 google-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/malue-ai/dazee-small/google-workspace.svg)](https://agentmods.dev/skills/malue-ai/dazee-small/google-workspace)
Your own site
<a href="https://agentmods.dev/skills/malue-ai/dazee-small/google-workspace"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/google-workspace.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,156 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 $0.00032 $0.01156
Opus 5 $0.00016 $0.00578
Sonnet 5 $0.00006 $0.00231
Haiku 4.5 $0.00003 $0.00116

Measured 7d ago against content hash c8ac8fff164f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

google-workspace 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 7d 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.

instances/xiaodazi/skills/google-workspace/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Workspace — 日历、邮件、云盘、文档

通过 Google 官方 MCP Server 操作 Google Calendar、Gmail、Drive 和 Docs。比第三方 CLI 工具更稳定可靠,支持 OAuth2 安全授权。

使用场景

日历

  • 用户说「明天下午 3 点帮我加个会议」
  • 用户说「这周有什么安排?」「下周三有空吗?」
  • 用户说「把今天的会议推迟一小时」
  • 用户说「帮我安排和 Alice 的 1-on-1,找个我们都有空的时间」

邮件

  • 用户说「有没有新邮件?」「今天收到了什么重要邮件?」
  • 用户说「帮我回复 Bob 的邮件,说同意他的方案」
  • 用户说「把这封邮件标记为重要」
  • 用户说「搜索上个月来自 [email protected] 的邮件」

云盘

  • 用户说「帮我在 Drive 里找那个季度报告」
  • 用户说「把这个文件上传到 Drive」
  • 用户说「共享那个文件给 [email protected]

前置条件

方式一:Google 官方 MCP Server(推荐)

  1. 安装 Google MCP Server:npm install -g @anthropic/google-mcp
  2. 首次运行时完成 OAuth2 授权(浏览器弹出 Google 登录页面)
  3. 授权后令牌自动存储,后续无需重复授权

方式二:Google API Key + Service Account

  1. 在 Google Cloud Console 创建项目并启用 Calendar/Gmail API
  2. 创建 OAuth 2.0 凭据或 Service Account
  3. 设置环境变量:export GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"

执行方式

日历操作

查询日程
工具: google_calendar_list_events
参数:
  calendar_id: "primary"
  time_min: "2026-02-26T00:00:00Z"
  time_max: "2026-02-27T00:00:00Z"
  max_results: 10
创建日程
工具: google_calendar_create_event
参数:
  calendar_id: "primary"
  summary: "产品评审会议"
  description: "讨论 Q1 产品路线图"
  start: "2026-02-27T15:00:00+08:00"
  end: "2026-02-27T16:00:00+08:00"
  attendees: ["[email protected]", "[email protected]"]
  location: "3 楼会议室 A"
修改日程
工具: google_calendar_update_event
参数:
  calendar_id: "primary"
  event_id: "xxx"
  start: "2026-02-27T16:00:00+08:00"  # 推迟一小时
  end: "2026-02-27T17:00:00+08:00"

邮件操作

搜索邮件
工具: gmail_search
参数:
  query: "from:[email protected] after:2026/01/01 subject:报告"
  max_results: 10
阅读邮件
工具: gmail_get_message
参数:
  message_id: "xxx"
发送邮件
工具: gmail_send_message
参数:
  to: "[email protected]"
  subject: "Re: 项目进度"
  body: "你好 Alice,附件是最新的进度报告..."
  cc: "[email protected]"

云盘操作

搜索文件
工具: google_drive_search
参数:
  query: "季度报告 2026"
  mime_type: "application/pdf"  # 可选
获取文件信息
工具: google_drive_get_file
参数:
  file_id: "xxx"

Read the full file on GitHub · 167 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. 7d ago First seen · 167 lines · 32 tokens per session scan A c8ac8fff164f

Subscribe to this mod's changes

google-workspace is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,156 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 2026-08-31.