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/fabioeloi/gws-cli-skill/gws-clinpx skills add fabioeloi/gws-cli-skill --skill gws-cligit clone --depth 1 https://github.com/fabioeloi/gws-cli-skillWrote 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/fabioeloi/gws-cli-skill/gws-cli)<a href="https://agentmods.dev/skills/fabioeloi/gws-cli-skill/gws-cli"><img src="https://agentmods.dev/badge/skills/fabioeloi/gws-cli-skill/gws-cli.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 | $0.00056 | $0.01334 |
| Opus 5 | $0.00028 | $0.00667 |
| Sonnet 5 | $0.00011 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
gws-cli 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gws-cli
Use this skill when the task should be executed through the Google Workspace CLI instead of handwritten HTTP requests or ad hoc API wrappers.
When to use this skill
- The user asks to interact with Google Drive, Gmail, Sheets, Docs, Slides, Calendar, Chat, Tasks, People, Meet, or Workspace Admin APIs.
- The user wants structured JSON output that is easy for an agent to inspect.
- The user needs to inspect Google API schemas before building a request.
- The user wants a repeatable CLI workflow that can run locally, in CI, or in a headless environment.
Required operating model
- Confirm that
gwsis installed and available onPATH. - Check authentication status before making API calls.
- Inspect the target method with
gws schemaorgws <service> --helpbefore composing flags. - Prefer read-only commands first.
- For write, update, or delete operations, confirm intent with the user before execution.
- Prefer
--dry-runwhen the command supports local validation and the operation is risky.
Quick start
# Install the CLI
npm install -g @googleworkspace/cli
# Check the binary and auth status
bash scripts/check-prereqs.sh
# Inspect command space
gws drive --help
gws schema drive.files.list
# Run a read-only command
gws drive files list --params '{"pageSize": 10}' --format json
Authentication workflow
Choose the lightest auth flow that satisfies the task.
Local interactive
gws auth setup
gws auth login
Service account
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/key.json
gws auth status
CI or headless flows
- Prefer exported credentials or service-account based execution.
- Never echo secrets back to the user.
- If credentials are missing, stop and ask for the appropriate auth setup instead of guessing.
More detail is in references/REFERENCE.md.
Command discovery workflow
Always inspect before executing.
# Browse resources and helper commands for a service
gws sheets --help
# Inspect a specific method schema
gws schema sheets.spreadsheets.values.get
What ships with it
2 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 · 153 lines · 56 tokens per session scan A 3687386d8c58
gws-cli is a skill published in the GitHub repository fabioeloi/gws-cli-skill (7 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 1,334 once invoked, about $0.0003 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
managing-google-workspace
Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search). Supports MCP tools or CLI via uvx workspace-mcp --cli. Provides tool routing, workflows, and parameter guidance for 114 tools. Triggers for "check my email"…
configure
Step-by-step setup wizard for the GWS connector. Walks through creating a GCP project, getting OAuth credentials, and connecting accounts.
reauth
Re-authorize a connected GWS account to refresh tokens or pick up new OAuth scopes without changing account settings.
add-account
Connect a new Google account to the GWS connector with a custom label. Supports per-account OAuth credentials for different organizations.
remove-account
Disconnect a Google account from the GWS connector and delete its tokens.
set-default
Set the default GWS account used when no account is specified.