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 Threat-Vector-Security/guardian-agent --skill google-workspacegit clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agentWrote 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/threat-vector-security/guardian-agent/google-workspace)<a href="https://agentmods.dev/skills/threat-vector-security/guardian-agent/google-workspace"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/google-workspace/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/threat-vector-security/guardian-agent/google-workspace"><img src="https://agentmods.dev/badge/skills/threat-vector-security/guardian-agent/google-workspace.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 | $0.00000 | $0.00448 |
| Opus 5.5 | $0.00000 | $0.00179 |
| Sonnet 5.5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
google-workspace 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 1mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace
Use the native Google Workspace tools for Gmail, Calendar, Drive, Docs, and Sheets.
Core rules:
- Authentication is handled by the connected Google Workspace integration. Never ask the user for OAuth access tokens.
- If the user asks for a generic email or inbox task and both Google Workspace and Microsoft 365 are available, ask which mailbox they mean before acting. Do not silently choose Gmail.
- For simple plain-text Gmail drafts, prefer
gmail_draft. - For simple plain-text Gmail sends, prefer
gmail_send. - For everything else, use
gws. - If you are unsure about a Google method or payload shape, use
gws_schemabefore guessing.
Workflow:
- Read first when the task is ambiguous or mutating.
- Prefer narrow reads over broad listings.
- For writes, confirm missing critical details only. Do not add unnecessary confirmation.
- Expect approvals for drafts, sends, and most write operations.
- If a Google action fails for auth, tell the user to connect Google Workspace in Settings. Do not ask for raw tokens.
How to use this skill:
- Gmail task: read
references/gmail.md - Calendar task: read
references/calendar.md - Drive, Docs, or Sheets task: read
references/drive-docs-sheets.md
General gws rules:
- Resource paths use spaces, not dots. Example:
users messages,users drafts,spreadsheets values. - Resource IDs and path/query fields go in
params. - Request bodies go in
json. - Gmail defaults to
userId: "me"when needed, but include it explicitly in examples and deliberate calls. - Calendar defaults to
calendarId: "primary"when needed, but include it explicitly when clarity matters.
Read only the domain reference you need for the current request. Do not load all references up front.
Gotchas
- Do not ask the user for raw OAuth tokens or API credentials.
- Do not silently pick Gmail when the mailbox provider is ambiguous.
- Do not use broad
gwscalls whengmail_draftorgmail_sendcovers the plain-text task cleanly.
What ships with it
4 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.
- 1mo ago First seen · 39 lines · 0 tokens per session scan A c8df62b27057
google-workspace is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (13 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 448 tokens. 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
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Tasks, Sheets, Docs, and Slides.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
wecomcli-sheet
A tool for managing WeCom online spreadsheets, including spreadsheet files, data, and subtables. WeCom is an enterprise collaboration platform.
intent-recognition
Load before you build any new kept workflow or Agent. It decides which one to build, or what to ask first. Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the…