gws is a command-line tool that provides one interface to Google Workspace services such as Drive, Gmail, Calendar, Sheets, Docs, Chat, and Admin. People and AI agents use it to automate Workspace tasks and receive structured JSON results, while its commands are generated dynamically from Google's Discovery Service. The catalogue contains skills and instructions for using gws.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/googleworkspace/clinpx agentmods add skills/googleworkspace/cli/gws-keepWrote 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/googleworkspace/cli/gws-keep)<a href="https://agentmods.dev/skills/googleworkspace/cli/gws-keep"><img src="https://agentmods.dev/badge/skills/googleworkspace/cli/gws-keep/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/googleworkspace/cli/gws-keep"><img src="https://agentmods.dev/badge/skills/googleworkspace/cli/gws-keep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00010 | $0.00451 |
| Opus 5.5 | $0.00004 | $0.00180 |
| Sonnet 5.5 | $0.00002 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
gws-keep 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.
What it actually says
keep (v1)
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
gws keep <resource> <method> [flags]
API Resources
media
download— Gets an attachment. To download attachment media via REST requires the alt=media query parameter. Returns a 400 bad request error if attachment media is not available in the requested MIME type.
notes
create— Creates a new note.delete— Deletes a note. Caller must have theOWNERrole on the note to delete. Deleting a note removes the resource immediately and cannot be undone. Any collaborators will lose access to the note.get— Gets a note.list— Lists notes. Every list call returns a page of results withpage_sizeas the upper bound of returned items. Apage_sizeof zero allows the server to choose the upper bound. The ListNotesResponse contains at mostpage_sizeentries. If there are more things left to list, it provides anext_page_tokenvalue. (Page tokens are opaque values.) To get the next page of results, copy the result'snext_page_tokeninto the next request'spage_token.permissions— Operations on the 'permissions' resource
Discovering Commands
Before calling any API method, inspect it:
# Browse resources and methods
gws keep --help
# Inspect a method's required params, types, and defaults
gws schema keep.<resource>.<method>
Use gws schema output to build your --params and --json flags.
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 · 50 lines · 10 tokens per session scan A 95a99760e826
gws-keep is a skill published in the GitHub repository googleworkspace/cli (31,694 stars, last pushed 13d ago), licensed Apache-2.0. It adds 10 tokens to every session and 451 once invoked, about $0.0000 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 2026-08-30.
Other skills, from other repositories
gum
Use when an agent needs Google API discovery, gum CLI calls, OAuth setup, or catalog-backed workflows.
gum-mcp
Use when an agent needs to wire or drive gum MCP tools for guarded Google API work.
gws-cli
Use the Google Workspace CLI to inspect schemas, authenticate safely, and run Google Workspace API commands. Use when the user wants to work with Drive, Gmail, Sheets, Docs, Calendar, Chat, Tasks, or other Google Workspace APIs through the gws command.
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
instagram-skill
How to use Instagram CLI to interact with Instagram from the command line on behalf of a user. Use this skill whenever the user wants to send or read Instagram messages, check their inbox, reply to or unsend messages, or automate any Instagram DM workflow via the CLI. This includes tasks phrased as "message X on…