google_workspace

Instructions for using Google Workspace through the gog command-line tool, including Gmail, Calendar, Drive, Contacts, Sheets, and Docs. It also explains setup and authentication.

In plain words
What is it for?
Searching and sending email, managing calendar events, finding or downloading Drive files, reading or editing Sheets, exporting Docs, and looking up contacts.
Why use it?
It tells the agent which Google services it can handle and how to connect the correct account, while avoiding unsupported Google Cloud or in-place Docs editing tasks.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ericwang915/pythonclaw/workspace
Any agent
npx skills add ericwang915/PythonClaw --skill workspace
Clone the repo
git clone --depth 1 https://github.com/ericwang915/PythonClaw

Made for: Claude Code, Codex.

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 997 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00067 $0.00997
Opus 5 $0.00034 $0.00498
Sonnet 5 $0.00013 $0.00199
Haiku 4.5 $0.00007 $0.00100

Measured 2d ago against content hash 786945cb1361, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (check_setup.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

pythonclaw/templates/skills/google/workspace/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Workspace (gog CLI)

Powered by gog — a Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

When to Use

  • Search Gmail, send email, read or manage messages
  • List or create calendar events
  • Search, list, or download Drive files
  • Read or edit Google Sheets (get, append, update, clear)
  • Export or read Google Docs content
  • List or search Contacts

When NOT to Use

  • Google Cloud Platform APIs (compute, storage, etc.)
  • Firebase or other non-Workspace services
  • Tasks that don't involve Gmail, Calendar, Drive, Sheets, Docs, or Contacts
  • In-place editing of Google Docs (gog supports read/export only)

Setup

  1. Install gog:

    brew install steipete/tap/gogcli
    
  2. Create OAuth credentials at Google Cloud Console (Desktop App), download client_secret.json.

  3. Authenticate:

    gog auth credentials /path/to/client_secret.json
    gog auth add [email protected] --services gmail,calendar,drive,contacts,sheets,docs
    
  4. Optionally set [email protected] to skip --account on each call.

Usage/Commands

Gmail

Action Command
Search mail gog gmail search 'newer_than:7d' --max 10
Send email gog gmail send --to [email protected] --subject "Hi" --body "Hello"
Read message gog gmail read <message_id>
Mark as read gog gmail labels modify <message_id> --remove UNREAD
List labels gog gmail labels list

Calendar

Action Command
List events gog calendar events --from 2026-02-23 --to 2026-02-28
Create event gog calendar create --title "Meeting" --start "2026-02-24T10:00" --end "2026-02-24T11:00"

Drive

Action Command
Search files gog drive search "query" --max 10
List files gog drive list --max 20
Download gog drive download <file_id> --out /tmp/file.pdf

Read the full file on GitHub · 106 lines

Files

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.

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. 2d ago First seen · 106 lines · 67 tokens per session scan A 786945cb1361

Subscribe to this mod's changes

google_workspace is a skill published in the GitHub repository ericwang915/PythonClaw (41 stars, last pushed 24d ago), licensed MIT. It adds 67 tokens to every session and 997 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

typescript-expert

TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.

fathah/hermes-desktop · 33 tokens

antfu

Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.

pdsuwwz/chatgpt-vue3-light-mvp · 52 tokens

conventional-commits

Conventional Commits specification for consistent, machine-readable git commit messages. Use when crafting commit messages, enforcing commitlint rules, or generating changelogs/releases.

pdsuwwz/chatgpt-vue3-light-mvp · 38 tokens

tencent-channel-community

腾讯频道(QQ频道)社区管理 skill(CLI 版)。频道创建/设置/搜索/加入/退出,成员管理/禁言/踢人,帖子发布/编辑/删除/移动/搜索,评论/回复/点赞,版块管理,分享链接解析,频道私信,加入设置管理,内容巡检,问答自动回复。涉及腾讯频道、频道帖子、频道成员相关任务时应优先使用。.

zhinjs/zhin · 99 tokens

migrate-zhin-plugin-runtime

Migrate legacy Zhin.js plugins and projects to the convention-based Plugin Runtime — from usePlugin/getPlugin/addCommand/addMiddleware/addComponent/addTool/addCron/declareConfig/useContext and mutable registries to definePlugin + capability directories + Scope/Token resources. Use this whenever a Zhin plugin fails to…

zhinjs/zhin · 178 tokens

zhin-audit

Audit Zhin.js monorepo for security vulnerabilities, performance bottlenecks, and architecture issues. Use when asked to "audit code", "check security", "find performance issues", "review architecture", "scan for vulnerabilities", "check memory leaks", or "review code quality".

zhinjs/zhin · 62 tokens