ac-tools-gsuite

ac-tools-gsuite is a skill for Claude Code from WaterplanAI/agentic-config. It costs 33 tokens per session (1,448 once invoked), scanned A, original, MIT.

A command-line integration for Google services such as Sheets, Docs, Slides, Drive, Gmail, Calendar, Contacts, and Tasks, with support for multiple accounts.

In plain words
What is it for?
Use it to manage spreadsheets, documents, presentations, files, email, calendars, contacts, and task lists through Google APIs.
Why use it?
It gives an agent one workflow for reading and changing Google files, messages, events, and tasks across work and personal accounts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the agentic-config plugin — 49 skills, 1 plugin shipped together

Good fit Use it to manage spreadsheets, documents, presentations, files, email, calendars, contacts, and task lists through Google APIs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waterplanai/agentic-config/ac-tools-gsuite
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 WaterplanAI/agentic-config --skill ac-tools-gsuite
Clone the repo
git clone --depth 1 https://github.com/WaterplanAI/agentic-config

Made for: Claude Code.

Or install agentic-config, the plugin that ships this one along with the rest of its 49 skills, 1 plugin.

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 ac-tools-gsuite

README.md
[![agentmods](https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-gsuite/github.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-gsuite)
Your own site
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-gsuite"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-gsuite/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.

agentmods 80×15 button for ac-tools-gsuite

Your own site · 80×15
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-gsuite"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-gsuite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,448 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 $0.00033 $0.01448
Opus 5 $0.00016 $0.00724
Sonnet 5 $0.00007 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 10d ago against content hash 66cef7b88ecc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ac-tools-gsuite 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 10d ago.

The scan reads SKILL.md. This mod also ships 15 executable files (tools/auth.py, tools/comments.py, tools/docs.py, …), 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.

packages/pi-ac-tools/skills/ac-tools-gsuite/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GSuite Skill

GSuite integration with multi-account support (work + personal).

Capabilities

  • Sheets: Read/write cells, create spreadsheets, append rows, manage sheets (list/add/rename/delete tabs)
  • Docs: Read/write documents, create docs, export to PDF/DOCX, manage tabs (list/create/rename/delete)
  • Slides: Read presentations, create slides, add content
  • Drive: List files, share, manage permissions, create folders
  • Gmail: Read/send/draft messages, search, manage labels
  • Calendar: List/create/update/delete events, manage calendars
  • Tasks: List/create/complete/delete tasks
  • People: Search contacts, resolve names to emails before operations
  • Comments: List/reply/resolve comments on any file type (Docs, Sheets, Slides) via Drive API, @ac convention for agent-directed comments
  • Auth: Multi-account management with account switching

Execution Mode

Use platform-native subagents when available (Task() / subagent tool). Legacy spawn-command flows are not supported.

Fallback: if subagent tooling is unavailable in the current runtime, execute GSuite tools directly via Bash.

Complexity Model Tier Use For
Simple reads Low-tier (haiku/flash-lite) auth.py status, gmail.py list, single API calls
Moderate Medium-tier (sonnet/flash) Multi-step operations, data processing, summarization
Complex High-tier (opus/pro) Cross-service operations, analysis requiring judgment

Execution patterns and examples are in cookbook/orchestration.md. Use direct CLI calls with explicit inputs/outputs.

Conventions

Tools: All PEP 723 uv scripts in tools/ (skill-relative). All support --help and --account/-a <email>. Verify exact tool names first (ls tools/) - naming is inconsistent (e.g., gcalendar vs docs).

Cookbook: <tool>.py -> cookbook/<tool>.md (MANDATORY read before executing). If cookbook missing, check <tool>.py --help directly.

Customization: <tool>.py -> ~/.agents/customization/gsuite/<tool>.md

Read the full file on GitHub · 155 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. 10d ago First seen · 155 lines · 33 tokens per session scan A 66cef7b88ecc

Subscribe to this mod's changes

ac-tools-gsuite is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,448 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 2026-08-30.