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 thewolffish/wolffish-app --skill googlegit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/google)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/google"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/google.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 694 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00021 | $0.06698 |
| Opus 5 | $0.00010 | $0.03349 |
| Sonnet 5 | $0.00004 | $0.01340 |
| Haiku 4.5 | $0.00002 | $0.00670 |
Grade A, and why
google 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 7d 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 — 809 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Workspace
Before doing anything: confirm the user is configured
Every tool here depends on (a) the gog binary being installed and (b) at least one Google account being authorized inside Wolffish. Both are user-facing setup steps that only work from the Settings panel — you cannot fix them from chat.
Always call google_accounts first. Every other google_* tool requires account as a parameter — there is no default account. The call fails with a clear error if you omit it. google_accounts returns the list of authorized account emails plus surfaces clear setup errors when something is missing:
Google Workspace is not installed. Open Wolffish → Settings → Services → Google Workspace and click Install.No Google account is authorized yet. Open Wolffish → Settings → Services → Google Workspace, upload your OAuth client JSON, and authorize at least one account.
If you see either of those errors (from google_accounts or from any other google_* tool), stop the workflow and relay the message to the user verbatim — they need to follow the exact path to Settings → Services → Google Workspace. Do not try to work around the missing setup with shell commands; gogcli stores credentials in the OS keyring and only the Settings flow wires it up correctly.
How it works
All tools use the gog CLI (gogcli) under the hood. Every command returns structured JSON. The gog binary must be installed and the user must have authenticated at least one Google account via Settings → Services → Google Workspace.
Account selection (REQUIRED on every call)
Every google_* tool except google_accounts requires an account parameter. There is no default and no "primary" — pick the email explicitly for every call. Calls without account fail with:
Missing required `account` parameter. Call google_accounts to get the list of authorized account emails, then pass one as `account` on this tool.
Identity-agnostic requests: fan out across all accounts
What ships with it
1 file 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.
- 7d ago First seen · 809 lines · 21 tokens per session scan A 32d608cdc2d8
google is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 6,698 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Tasks, Sheets, Docs, and Slides.
google-workspace
Manage Gmail, Google Calendar, Drive, Sheets, Docs, Contacts, and Tasks via the gogcli CLI. TRIGGER: "gmail", "google calendar", "google drive", "google sheets". NOT FOR: outlook-assistant, xlsx, docx use cases.
google-sheets-automation
Lightweight Google Sheets integration with standalone OAuth authentication. No MCP server required. Full read/write access.
google-workspace
Use the native Google Workspace tools for Gmail, Calendar, Drive, Docs, and Sheets.
office-productivity
Office productivity workflow covering document creation, spreadsheet automation, presentation generation, and integration with LibreOffice and Microsoft Office formats.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.