google

google is a skill for Claude Code from odyssey4me/agent-skills. It costs 45 tokens per session (2,359 once invoked), scanned A, original, Apache-2.0.

A command-line connection to Google Workspace, the set of Google services for email, calendars, files, documents, spreadsheets, and presentations.

In plain words
What is it for?
Use it to search Gmail, manage Calendar events, find Drive files, read Docs, update Sheets, and work with Slides through the gog command-line tool.
Why use it?
It gives a coding agent one documented way to work with these Google services after authentication, rather than handling each service separately.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: built for openclaw.

Good fit Use it to search Gmail, manage Calendar events, find Drive files, read Docs, update Sheets, and work with Slides through the gog command-line tool.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/odyssey4me/agent-skills/google
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 odyssey4me/agent-skills --skill google
Clone the repo
git clone --depth 1 https://github.com/odyssey4me/agent-skills

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/odyssey4me/agent-skills/google.svg)](https://agentmods.dev/skills/odyssey4me/agent-skills/google)
Your own site
<a href="https://agentmods.dev/skills/odyssey4me/agent-skills/google"><img src="https://agentmods.dev/badge/skills/odyssey4me/agent-skills/google.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 4 Sept 2026
  • Snyk warn 4 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, 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 41
    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.
  • high Privilege Escalation · line 42
    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 $0.00045 $0.02359
Opus 5 $0.00023 $0.01179
Sonnet 5 $0.00009 $0.00472
Haiku 4.5 $0.00005 $0.00236

Measured 3d ago against content hash 16b7b9b9fc6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

google scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL https://github.com/openclaw/gogcli/releases/latest/download/gogcli_VERSION_linux_amd64.tar.gz | tar xz
skills/google/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Workspace Skill

This skill provides Google Workspace integration using the gog CLI (gogcli). The agent calls gog directly for all operations.

Prerequisites

Install the gog binary (CI-validated version is listed in the frontmatter above):

# Homebrew
brew install openclaw/tap/gogcli

# Manual (Linux amd64)
curl -sL https://github.com/openclaw/gogcli/releases/latest/download/gogcli_VERSION_linux_amd64.tar.gz | tar xz
mv gog ~/.local/bin/

See configuration.md for container and MCP server alternatives.

Authentication

# Import credentials.json from Google Cloud Console
gog auth credentials set /path/to/credentials.json

# Authorize with only the services you need (opens browser)
gog auth add [email protected] --services gmail,calendar,drive,docs,sheets,slides

# Verify
gog auth doctor

Quick Reference

gog gmail search "is:unread"                    # Search email
gog calendar events --today                     # Today's events
gog drive search "quarterly report"             # Search files
gog docs cat <docId>                            # Read a document
gog sheets get <spreadsheetId> "Sheet1!A1:D10"  # Read spreadsheet range
gog slides info <presentationId>                # Presentation metadata

All commands support --json for structured output and --plain for TSV.

Commands

Gmail

# Search
gog gmail search "from:[email protected] newer_than:7d"
gog gmail search "is:unread label:inbox" --max 20

# Read
gog gmail get <messageId>
gog gmail thread get <threadId>
gog gmail labels list

# Organize
gog gmail mark-read <messageId>
gog gmail unread <messageId>
gog gmail archive <messageId>
gog gmail trash <messageId>

# Send
gog gmail send --to "[email protected]" --subject "Hello" --body "Message body"
gog gmail reply <messageId> --body "Reply text"
gog gmail forward <messageId> --to "[email protected]"

# Drafts
gog gmail drafts list
gog gmail drafts create --to "[email protected]" --subject "Draft" --body "Content"
gog gmail drafts send <draftId>

Read the full file on GitHub · 293 lines

Files

What ships with it

9 files 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. 3d ago Changed 16b7b9b9fc6e
  2. 7d ago First seen · 293 lines · 45 tokens per session scan A a8f45eed0041

Subscribe to this mod's changes

google is a skill published in the GitHub repository odyssey4me/agent-skills (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,359 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.