Borrowing it
Nothing to install: this file belongs to chrizbo/agentics-beyond-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chrizbo/agentics-beyond-code/main/.github/skills/google-workspace-agent-builder/SKILL.mdgit clone --depth 1 https://github.com/chrizbo/agentics-beyond-codeWrote 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/chrizbo/agentics-beyond-code/google-workspace-agent-builder)<a href="https://agentmods.dev/skills/chrizbo/agentics-beyond-code/google-workspace-agent-builder"><img src="https://agentmods.dev/badge/skills/chrizbo/agentics-beyond-code/google-workspace-agent-builder/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/chrizbo/agentics-beyond-code/google-workspace-agent-builder"><img src="https://agentmods.dev/badge/skills/chrizbo/agentics-beyond-code/google-workspace-agent-builder.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 | $0.00139 | $0.05768 |
| Opus 5.5 | $0.00056 | $0.02307 |
| Sonnet 5.5 | $0.00028 | $0.01154 |
| Haiku 4.5 | $0.00014 | $0.00577 |
Grade A, and why
google-workspace-agent-builder 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 18d 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 — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace Agent Builder
Turn a selected workflow into a Google Workspace automation, usually a
Workspace Studio flow with an Ask Gemini step and a Studio skill, that a team
can run where its mail, documents, and chat already live. Follow the
Claude-native builder's source-first approach: preserve the workflow's purpose,
evidence, readable artifacts, and human interpretation points while adapting
its execution to Google. This is one of the platform builders alongside
github-workflow-builder, claude-native-workflow-builder,
productboard-agent-builder, and atlassian-agent-builder. Choosing which
workflows to adopt, and whether Google is the right platform, belongs to
agentic-workflow-planner.
Unlike the other builders, which Google surface is usable depends heavily on the team's Workspace plan, add-ons, and admin settings. Never assume Workspace Studio is available or has room for the workflow; run Choose the Google surface for this plan before drafting.
Choose the target and source
Keep these surfaces distinct; evidence about one does not prove another:
- Workspace Studio flow: a starter (schedule, Gmail, Calendar, Sheets, Drive, Forms, Chat, manual, or a custom starter), then steps: Ask Gemini, Workspace actions, NotebookLM, Gemini Enterprise agents, integrations, webhooks, and Apps Script custom steps. Counts against the Studio run quota.
- Studio skill: reusable instructions (a codified procedure) usable on demand in Gemini in Workspace and from an Ask Gemini step in a flow. The equivalent of a Rovo agent's Behavior or a Spark skill.
- Apps Script custom step or custom starter: developer path for logic or triggers Studio lacks, including calls to GitHub. Needs code, an owner, and admin enablement.
- Apps Script alone: time-driven or event triggers with no Gemini step. Prefer it for deterministic rules or when Studio's quota or edition blocks the workflow.
- Gemini Enterprise agent: Agent Designer agents under a separate Google Cloud license. Offer only when the org already has it or the workflow needs enterprise-data agents.
- External agent through the Workspace MCP server: Claude or another
client acting on Gmail, Drive, Docs, Sheets, Calendar, and Chat. This runs
outside Google; route it to
claude-native-workflow-builder.
What ships with it
6 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.
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.
- 18d ago Changed · +16 lines d4005267f27b
- 25d ago First seen · 409 lines · 139 tokens per session scan A 2443f5309b0f
google-workspace-agent-builder is a skill published in the GitHub repository chrizbo/agentics-beyond-code (34 stars, last pushed 4d ago), licensed MIT. It adds 139 tokens to every session and 5,768 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.