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 agentmods add skills/mitsuhiko/agent-stuff/google-workspacenpx skills add mitsuhiko/agent-stuff --skill google-workspacegit clone --depth 1 https://github.com/mitsuhiko/agent-stuffWrote 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/mitsuhiko/agent-stuff/google-workspace)<a href="https://agentmods.dev/skills/mitsuhiko/agent-stuff/google-workspace"><img src="https://agentmods.dev/badge/skills/mitsuhiko/agent-stuff/google-workspace.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00904 |
| Opus 5 | $0.00020 | $0.00452 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
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 4d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace
Use this skill for Google Workspace tasks (Gmail, Drive, Calendar, Docs, Sheets, etc.).
Files
scripts/auth.js— OAuth login/status/clear + account enumerationscripts/workspace.js— JavaScript execution based API runner
Account model (multi-account)
This skill is profile-based by email address.
- There is no default account.
- Every API call must specify
--email <[email protected]>. - Tokens are stored per-email under
~/.pi/google-workspace/tokens/.
Before running API calls, discover available signed-in accounts:
node scripts/auth.js accounts
Usage
Always use exec and always provide --email.
node scripts/workspace.js exec --email [email protected] <<'JS'
const me = await workspace.whoAmI();
const files = await workspace.call('drive', 'files.list', {
pageSize: 5,
fields: 'files(id,name,mimeType)',
});
return { me, files: files.files };
JS
Available inside exec scripts:
auth(authorized OAuth client)google(googleapisroot)workspace.accountEmail(selected profile email)workspace.call(service, methodPath, params, {version})workspace.service(service, {version})workspace.whoAmI()
Optional flags:
--timeout <ms>(default 30000, max 300000)--scopes s1,s2--script 'return 42'
Agent guidance
- Prefer one
execscript per user request. - Keep payloads small (
fields,maxResults, minimal props). - Use
Promise.allfor independent requests. - Never print token contents.
- If the user did not specify an account, run
node scripts/auth.js accountsand choose/confirm an explicit email. - If auth fails, first run
node scripts/auth.js accountsto see known profiles. - If account mismatch is possible, run
workspace.whoAmI()in the selected profile. - On 401/403/unauthorized errors, switch account (
--email ...) or re-login that specific profile.
Unauthorized/account-switch playbook
If a request fails with unauthorized/forbidden/insufficient permissions:
What ships with it
5 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.
- 4d ago First seen · 138 lines · 40 tokens per session scan A 35c23e0802a3
google-workspace is a skill published in the GitHub repository mitsuhiko/agent-stuff (3,044 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 904 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
xlsx-author
Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
octo-docs
Docs domain — create and govern documents, read and incrementally edit a doc's live body, read and batch-edit spreadsheet cells (dims + images), read and batch-edit whiteboard scenes, members and sharing, inline comments, versions/snapshots, and attachment metadata as a bot. Load after octo-shared.
cli-anything-wps
WPS Office CLI — JSON数据驱动PPT自动生成 + 命令行操控WPS文字/表格/演示文稿.