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.
npx skills add WaterplanAI/agentic-config --skill ac-tools-gsuitegit clone --depth 1 https://github.com/WaterplanAI/agentic-configWrote 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.
[](https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-gsuite)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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,
@acconvention 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
What ships with it
35 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.
- assets/api-reference.md 888 B
- assets/enterprise-setup.md 3.1 KB
- assets/oauth-setup.md 2.4 KB
- assets/scopes.yml 2.4 KB
- cookbook/auth.md 4.5 KB
- cookbook/comments.md 11 KB
- cookbook/docs.md 4.1 KB
- cookbook/drive.md 1.4 KB
- cookbook/extra.md 2.2 KB
- cookbook/gcalendar.md 14 KB
- cookbook/gdate.md 1.6 KB
- cookbook/gmail.md 2.8 KB
- cookbook/mermaid.md 3.4 KB
- cookbook/orchestration.md 2.2 KB
- cookbook/people.md 4.3 KB
- cookbook/preferences.md 7.3 KB
- cookbook/sheets.md 2.9 KB
- cookbook/tasks.md 1.1 KB
- prompts/docs-template.md 1.2 KB
- prompts/sheets-template.md 1.4 KB
- tools/auth.py 19 KB runs code
- tools/comments.py 4.7 KB runs code
- tools/docs.py 29 KB runs code
- tools/drive.py 34 KB runs code
- tools/gcalendar.py 27 KB runs code
- tools/gdate.py 5.8 KB runs code
- tools/gmail.py 26 KB runs code
- tools/md2docs.py 29 KB runs code
- tools/mermaid.py 9.4 KB runs code
- tools/people.py 5.4 KB runs code
- tools/setup.py 6.1 KB runs code
- tools/sheets.py 17 KB runs code
- tools/slides.py 13 KB runs code
- tools/tasks.py 17 KB runs code
- tools/utils.py 3.5 KB runs code
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.
- 10d ago First seen · 155 lines · 33 tokens per session scan A 66cef7b88ecc
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.
Other skills, from other repositories
extract-rental-applications-to-spreadsheet
Extract applicant details from rental application PDFs and generate a side-by-side XLSX for comparing income, employment, and move-in dates.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
composio-delivery
Delivers the finalized analyst brief to Slack, Notion, Google Sheets, and Gmail via authenticated Composio tools. Use whenever a completed, grounded brief must be distributed and logged.
ai-csv-excel-merger
A tool for combining CSV and Excel materials into one organized result while identifying conflicting fields.
data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.