googleworkspace

googleworkspace is a skill for Claude Code, Codex from laude-institute/headlong. It costs 22 tokens per session (1,273 once invoked), scanned A, original, Apache-2.0.

A command-line interface for working with Google Drive, Gmail, Calendar, Sheets, Docs, Chat, and other Google Workspace services. A command-line interface lets you perform these actions by typing commands instead of using each web app.

In plain words
What is it for?
Use it to read or update Workspace data, send emails, manage files and calendar items, edit documents or spreadsheets, and automate repeatable tasks.
Why use it?
It provides one scriptable way to access Google Workspace and preview requests before sending them.

Skill for Claude CodeCodex

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

Good fit Use it to read or update Workspace data, send emails, manage files and calendar items, edit documents or spreadsheets, and automate repeatable tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/laude-institute/headlong/googleworkspace
About the project

Headlong is a Bash-based agent microharness for running language-model agents in persistent, self-directed loops. People use it to create agents that maintain ongoing interests and projects, interact through shell commands, and share one stream of conversations across a team and chat services.

laude-institute/headlong · 1,126 stars · on GitHub · headlong.ai

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 laude-institute/headlong --skill googleworkspace
Clone the repo
git clone --depth 1 https://github.com/laude-institute/headlong

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 googleworkspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/laude-institute/headlong/googleworkspace.svg)](https://agentmods.dev/skills/laude-institute/headlong/googleworkspace)
Your own site
<a href="https://agentmods.dev/skills/laude-institute/headlong/googleworkspace"><img src="https://agentmods.dev/badge/skills/laude-institute/headlong/googleworkspace.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,273 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 28
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00022 $0.01273
Opus 5 $0.00011 $0.00636
Sonnet 5 $0.00004 $0.00255
Haiku 4.5 $0.00002 $0.00127

Measured 8d ago against content hash 8520c992cc36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

googleworkspace 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 8d 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.

skills/googleworkspace/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

googleworkspace — Google Workspace via the gws CLI

Overview

The gws CLI provides access to Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, and more). Commands are dynamically generated from Google's Discovery Service.

gws <service> <resource> <method> [flags]

Helper commands (prefixed with +) provide shortcuts for common workflows.

Authentication

# Browser-based OAuth (interactive, one-time)
gws auth login

# Or use an existing access token
export GOOGLE_WORKSPACE_CLI_TOKEN=$(gcloud auth print-access-token)

Global flags

Flag Description
--params '{...}' URL/query parameters (JSON)
--json '{...}' Request body (JSON)
--dry-run Preview request without calling the API
--page-all Auto-paginate all results (NDJSON output)
--upload <PATH> Upload file content (multipart)
--format <FMT> Output format: json (default), table, yaml, csv

Discovering commands

Always inspect before calling an unfamiliar method:

gws <service> --help
gws schema <service>.<resource>.<method>

Gmail

# Send an email
gws gmail +send --to [email protected] --subject "Hello" --body "Hi there"

# Unread inbox summary
gws gmail +triage

# Read a message body
gws gmail +read --message-id MESSAGE_ID

# Reply to a message (threading handled automatically)
gws gmail +reply --message-id MESSAGE_ID --body "Thanks!"

# Reply-all
gws gmail +reply-all --message-id MESSAGE_ID --body "Acknowledged"

# Forward a message
gws gmail +forward --message-id MESSAGE_ID --to [email protected]

# Watch for new emails (streams NDJSON)
gws gmail +watch

# List messages via API
gws gmail users messages list --params '{"maxResults": 10}'

Calendar

# Show upcoming events
gws calendar +agenda

# Show agenda in a specific timezone
gws calendar +agenda --timezone America/New_York

# Create an event
gws calendar +insert --title "Standup" --time "2026-05-02T09:00:00"

# List events via API
gws calendar events list --params '{"calendarId": "primary", "maxResults": 5}'

# Check free/busy
gws calendar freebusy query --json '{"timeMin": "...", "timeMax": "...", "items": [{"id": "primary"}]}'

Read the full file on GitHub · 184 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. 8d ago First seen · 184 lines · 22 tokens per session scan A 8520c992cc36

Subscribe to this mod's changes

googleworkspace is a skill published in the GitHub repository laude-institute/headlong (1,126 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,273 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 2026-08-30.