File: README.md Copy Chapter

gws

One CLI for all of Google Workspace — built for humans and AI agents.
Drive, Gmail, Calendar, and every Workspace API. Zero boilerplate. Structured JSON output. 40+ agent skills included.

[!NOTE]
This is not an officially supported Google product.

⬇️ Download the latest release for your OS

gws doesn't ship a static list of commands. It reads Google's own Discovery Service at runtime and builds its entire command surface dynamically. When Google Workspace adds an API endpoint or method, gws picks it up automatically.

[!IMPORTANT]
This project is under active development. Expect breaking changes as we march toward v1.0.

Contents Copy Chapter

• Prerequisites
• Installation
• Quick Start
• Why gws?
• Authentication
• AI Agent Skills
• Advanced Usage
• Environment Variables
• Exit Codes
• Architecture
• Troubleshooting
• Development

Prerequisites Copy Chapter

• Node.js 18+ — for npm install (or download a pre-built binary from GitHub Releases)
• A Google Cloud project — required for OAuth credentials. You can create one via the Google Cloud Console or with the gcloud CLI or with the gws auth setup command.
• A Google account with access to Google Workspace

Installation Copy Chapter

The recommended way to install gws is to download the pre-built binary for your OS and architecture from the GitHub Releases page. Extract the archive and place the gws binary in your $PATH.

For convenience, you can also use npm to automate downloading the appropriate binary from GitHub Releases:

npm install @googleworkspace/cli

Or build from source:

cargo install --git https://github.com/googleworkspace/cli --locked

A Nix flake is also available at github:googleworkspace/cli

nix run github:googleworkspace/cli

On macOS and Linux, you can also install via Homebrew:

brew install googleworkspace-cli

Quick Start Copy Chapter

gws auth setup     # walks you through Google Cloud project config
gws auth login     # subsequent OAuth login
gws drive files list --params '{"pageSize": 5}'

Why gws? Copy Chapter

For humans — stop writing curl calls against REST docs. gws gives you --help on every resource, --dry-run to preview requests, and auto‑pagination.

For AI agents — every response is structured JSON. Pair it with the included agent skills and your LLM can manage Workspace without custom tooling.

# List the 10 most recent files
gws drive files list --params '{"pageSize": 10}'

# Create a spreadsheet
gws sheets spreadsheets create --json '{"properties": {"title": "Q1 Budget"}}'

# Send a Chat message
gws chat spaces messages create \
  --params '{"parent": "spaces/xyz"}' \
  --json '{"text": "Deploy complete."}' \
  --dry-run

# Introspect any method's request/response schema
gws schema drive.files.list

# Stream paginated results as NDJSON
gws drive files list --params '{"pageSize": 100}' --page-all | jq -r '.files[].name'

Authentication Copy Chapter

The CLI supports multiple auth workflows so it works on your laptop, in CI, and on a server.

Which setup should I use? Copy Section

Interactive (local desktop) Copy Section

Credentials are encrypted at rest (AES-256-GCM) with the key stored in your OS keyring (or ~/.config/gws/.encryption_key when GOOGLE_WORKSPACE_CLI_KEYRING_BACKEND=file).

gws auth setup       # one-time: creates a Cloud project, enables APIs, logs you in
gws auth login       # subsequent scope selection and login

gws auth setup requires the gcloud CLI. If you don't have gcloud, use the manual setup below instead.

[!WARNING]
Scope limits in testing mode: If your OAuth app is unverified (testing mode),
Google limits consent to ~25 scopes. The recommended scope preset includes 85+
scopes and will fail for unverified apps (especially for @gmail.com accounts).
Choose individual services instead to filter the scope picker:

bash Copy

gws auth login -s drive,gmail,sheets

Manual OAuth setup (Google Cloud Console) Copy Section

Use this when gws auth setup cannot automate project/client creation, or when you want explicit control.

1. Open Google Cloud Console in the target project:
   • OAuth consent screen: https://console.cloud.google.com/apis/credentials/consent?project=
   • Credentials: https://console.cloud.google.com/apis/credentials?project=
2. Configure OAuth branding/audience if prompted:
   • App type: External (testing mode is fine)
3. Add your account under Test users
4. Create an OAuth client:
   • Type: Desktop app
5. Download the client JSON and save it to:
   • ~/.config/gws/client_secret.json

[!IMPORTANT]
You must add yourself as a test user. In the OAuth consent screen, click
Test users → Add users and enter your Google account email. Without this,
login will fail with a generic "Access blocked" error.

Then run:

gws auth login

Browser-assisted auth (human or agent) Copy Section

You can complete OAuth either manually or with browser automation.

• Human flow: run gws auth login, open the printed URL, approve scopes.
• Agent-assisted flow: the agent opens the URL, selects account, handles consent prompts, and returns control once the localhost callback succeeds.

If consent shows "Google hasn't verified this app" (testing mode), click Continue.
If scope checkboxes appear, select required scopes (or Select all) before continuing.

Headless / CI (export flow) Copy Section

1. Complete interactive auth on a machine with a browser.
2. Export credentials:
   bash Copy

   gws auth export --unmasked > credentials.json

3. On the headless machine:
   bash Copy

   export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/credentials.json
   gws drive files list   # just works

Service Account (server-to-server) Copy Section

Point to your key file; no login needed.

export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=/path/to/service-account.json
gws drive files list

Pre-obtained Access Token Copy Section

Useful when another tool (e.g. gcloud) already mints tokens for your environment.

export GOOGLE_WORKSPACE_CLI_TOKEN=$(gcloud auth print-access-token)

Precedence Copy Section

Environment variables can also live in a .env file.

AI Agent Skills Copy Chapter

The repo ships 100+ Agent Skills (SKILL.md files) — one for every supported API, plus higher-level helpers for common workflows and 50 curated recipes for Gmail, Drive, Docs, Calendar, and Sheets. See the full Skills Index for the complete list.

# Install all skills at once
npx skills add https://github.com/googleworkspace/cli

# Or pick only what you need
npx skills add https://github.com/googleworkspace/cli/tree/main/skills/gws-drive
npx skills add https://github.com/googleworkspace/cli/tree/main/skills/gws-gmail

OpenClaw setup

# Symlink all skills (stays in sync with repo)
ln -s $(pwd)/skills/gws-* ~/.openclaw/skills/

# Or copy specific skills
cp -r skills/gws-drive skills/gws-gmail ~/.openclaw/skills/

The gws-shared skill includes an install block so OpenClaw auto-installs the CLI via npm if gws isn't on PATH.

Gemini CLI Extension Copy Chapter

1. Authenticate the CLI first:

   bash Copy

   gws auth setup

2. Install the extension into the Gemini CLI:

   bash Copy

   gemini extensions install https://github.com/googleworkspace/cli

Installing this extension gives your Gemini CLI agent direct access to all gws commands and Google Workspace agent skills. Because gws handles its own authentication securely, you simply need to authenticate your terminal once prior to using the agent, and the extension will automatically inherit your credentials.

Advanced Usage Copy Chapter

Multipart Uploads Copy Section

gws drive files create --json '{"name": "report.pdf"}' --upload ./report.pdf

Pagination Copy Section

Google Sheets — Shell Escaping Copy Section

Sheets ranges use ! which bash interprets as history expansion. Always wrap values in single quotes:

# Read cells A1:C10 from "Sheet1"
gws sheets spreadsheets values get \
  --params '{"spreadsheetId": "SPREADSHEET_ID", "range": "Sheet1!A1:C10"}'

# Append rows
gws sheets spreadsheets values append \
  --params '{"spreadsheetId": "ID", "range": "Sheet1!A1", "valueInputOption": "USER_ENTERED"}' \
  --json '{"values": [["Name", "Score"], ["Alice", 95]]}'

Helper Commands Copy Section

Some services ship hand-crafted helper commands alongside the auto-generated Discovery surface. Helper commands are prefixed with + so they are visually distinct and never collide with Discovery-generated method names.

Time-aware helpers (+agenda, +standup-report, +weekly-digest, +meeting-prep) automatically use your Google account timezone (fetched from Calendar Settings API and cached for 24 hours). Override with --timezone/--tz on +agenda, or set the --timezone flag for explicit control.

Run gws <service> --help to see both Discovery methods and helper commands together.

gws gmail --help      # shows +send, +reply, +reply-all, +forward, +triage, +watch …
gws calendar --help   # shows +insert, +agenda …
gws drive --help      # shows +upload …

Full helper reference:

Examples:

# Send an email
gws gmail +send --to [email protected] --subject "Hello" --body "Hi there"

# Reply to a message
gws gmail +reply --message-id MESSAGE_ID --body "Thanks!"

# Append a row to a spreadsheet
gws sheets +append --spreadsheet SPREADSHEET_ID --values "Alice,95"

# Show today's calendar agenda
gws calendar +agenda

# Upload a file to Drive
gws drive +upload ./report.pdf --name "Q1 Report"

# Morning standup summary
gws workflow +standup-report

# Show today's agenda in a specific timezone
gws calendar +agenda --today --timezone America/New_York

Model Armor (Response Sanitization) Copy Section

Integrate Google Cloud Model Armor to scan API responses for prompt injection before they reach your agent.

gws gmail users messages get --params '...' \
  --sanitize "projects/P/locations/L/templates/T"

Environment Variables Copy Chapter

All variables are optional. See .env.example for a copy-paste template.

Environment variables can also be set in a .env file (loaded via dotenvy).

Exit Codes Copy Chapter

gws uses structured exit codes so scripts can branch on the failure type without parsing error output.

gws drive files list --params '{"fileId": "bad"}'
echo $?   # 1 — API error

gws unknown-service files list
echo $?   # 3 — validation error (unknown service)

Architecture Copy Chapter

gws uses a two-phase parsing strategy:

1. Read argv[1] to identify the service (e.g. drive)
2. Fetch the service's Discovery Document (cached 24 h)
3. Build a clap::Command tree from the document's resources and methods
4. Re-parse the remaining arguments
5. Authenticate, build the HTTP request, execute

All output — success, errors, download metadata — is structured JSON.

Troubleshooting Copy Chapter

"Access blocked" or 403 during login Copy Section

Your OAuth app is in testing mode and your account is not listed as a test user.

Fix: Open the OAuth consent screen in your GCP project → Test users → Add users → enter your Google account email. Then retry gws auth login.

"Google hasn't verified this app" Copy Section

Expected when your app is in testing mode. Click Advanced → Go to <app name> (unsafe) to proceed. This is safe for personal use; verification is only required to publish the app to other users.

Too many scopes / consent screen error Copy Section

Unverified (testing mode) apps are limited to ~25 OAuth scopes. The recommended scope preset includes many scopes and will exceed this limit.

Fix: Select only the scopes you need:

gws auth login --scopes drive,gmail,calendar

`gcloud` CLI not found Copy Section

gws auth setup requires the gcloud CLI to automate project creation. You have three options:

1. Install gcloud and use gcloud directly.
2. Re-run gws auth setup which wraps gcloud calls.
3. Skip gcloud entirely — set up OAuth credentials manually in the Cloud Console

`redirect_uri_mismatch` Copy Section

The OAuth client was not created as a Desktop app type. In the Credentials page, delete the existing client, create a new one with type Desktop app, and download the new JSON.

API not enabled — `accessNotConfigured` Copy Section

If a required Google API is not enabled for your GCP project, you will see a
403 error with reason accessNotConfigured:

{
  "error": {
    "code": 403,
    "message": "Gmail API has not been used in project 549352339482 ...",
    "reason": "accessNotConfigured",
    "enable_url": "https://console.developers.google.com/apis/api/gmail.googleapis.com/overview?project=549352339482"
  }
}

gws also prints an actionable hint to stderr:

💡 API not enabled for your GCP project.
   Enable it at: https://console.developers.google.com/apis/api/gmail.googleapis.com/overview?project=549352339482
   After enabling, wait a few seconds and retry your command.

Steps to fix:

1. Click the enable_url link (or copy it from the enable_url JSON field).
2. In the GCP Console, click Enable.
3. Wait ~10 seconds, then retry your gws command.

[!TIP]
You can also run gws auth setup which walks you through enabling all required
APIs for your project automatically.

Development Copy Chapter

cargo build                       # dev build
cargo clippy -- -D warnings       # lint
cargo test                        # unit tests
./scripts/coverage.sh             # HTML coverage report → target/llvm-cov/html/

License Copy Chapter

Apache-2.0

Disclaimer Copy Chapter

[!CAUTION]
This is not an officially supported Google product.

File: crates/google-workspace-cli/src/helpers/README.md Copy Chapter

Helper Commands (`+verb`) — Guidelines

Design Principle Copy Chapter

The core design of gws is schema-driven: commands are dynamically generated from Google Discovery Documents at runtime. This avoids maintaining a hardcoded, unbounded argument surface. Helpers must complement this design, not duplicate it.

When a Helper is Justified Copy Chapter

A +helper command should exist only when it provides value that Discovery-based commands cannot:

Litmus test: Can the user achieve the same result with gws <service> <resource> <method> --params '{...}'? If yes, don't add a helper.

Anti-Patterns Copy Chapter

❌ Anti-pattern 1: Single API Call Wrapper Copy Section

If a helper wraps one API call that Discovery already exposes, reject it.

Real example: +revisions (PR #563) wrapped gws drive files-revisions list — same single API call, zero added value.

❌ Anti-pattern 2: Unbounded Flag Accumulation Copy Section

Adding flags to expose data that is already in the API response creates unbounded surface area.

Real example: --thread-id, --delivered-to, --sent-last on +triage (PR #597) — all three values are already present in the Gmail API response. Agents and users should extract them with --format or jq, not new flags.

Why this is harmful: Every API response contains dozens of fields. If we add a flag for each one, helpers become unbounded maintenance burdens — the exact problem Discovery-driven design solves.

❌ Anti-pattern 3: Duplicating Discovery Parameters Copy Section

Don't re-expose Discovery-defined parameters (e.g., pageSize, fields, orderBy) as custom helper flags. Use --params passthrough instead.

Flag Design Rules Copy Chapter

Helper flags must control orchestration logic, not API parameters or output fields.

✅ Good Flags (control orchestration) Copy Section

❌ Bad Flags (expose API response data) Copy Section

Decision Checklist for New Flags Copy Section

1. Does this flag control what API call to make or how to orchestrate multiple calls? → ✅ Add it
2. Does this flag control what data appears in output? → ❌ Use --format/jq
3. Does this flag duplicate a Discovery parameter? → ❌ Use --params
4. Could the user achieve this with existing flags + post-processing? → ❌ Don't add it

Architecture Copy Chapter

Helpers are implemented using the Helper trait defined in mod.rs.

• inject_commands: Adds subcommands to the main service command. All helper commands are always shown regardless of authentication state.
• handle: Implementation of the command logic. Returns Ok(true) if the command was handled, or Ok(false) to let the default raw resource handler attempt to handle it.

Adding a New Helper — Checklist Copy Chapter

1. Passes the litmus test — cannot be done with a single Discovery command
2. Flags are bounded — only flags controlling orchestration, not API params/output
3. Uses shared infrastructure:
   • crate::client::build_client() for HTTP
   • crate::validate::validate_resource_name() for user-supplied resource IDs
   • crate::validate::encode_path_segment() for URL path segments
   • crate::output::sanitize_for_terminal() for error messages
4. Has tests — at minimum: command registration, required args, happy path
5. Supports --dry-run where the helper creates or mutates resources

Development Steps Copy Section

1. Create src/helpers/<service>.rs
2. Implement the Helper trait
3. Register it in src/helpers/mod.rs
4. Prefix the command with + (e.g., +create)

File: crates/google-workspace-cli/README.md Copy Chapter

google-workspace-cli

One CLI for all of Google Workspace — built for humans and AI agents.

gws dynamically generates its command surface at runtime by reading Google's Discovery Service. Drive, Gmail, Calendar, and every Workspace API — zero boilerplate, structured JSON output, 40+ agent skills included.

Install Copy Chapter

Download the pre-built binary for your OS and architecture from the GitHub Releases page.

Alternatively, you can use package managers as a convenience layer:

npm install @googleworkspace/cli    # npm (downloads GitHub release binary)
cargo install google-workspace-cli     # crates.io
nix run github:googleworkspace/cli     # nix

Quick Start Copy Chapter

gws auth login
gws drive files list --params '{"pageSize": 5}'
gws gmail users.messages list --params '{"maxResults": 3}'

Documentation Copy Chapter

See the full README for authentication setup, helper commands, agent skills, and more.

License Copy Chapter

Apache-2.0 — see LICENSE.

File: crates/google-workspace/README.md Copy Chapter

google-workspace

Core Rust library for interacting with Google Workspace APIs via the Discovery Service.

This crate provides the foundational types and utilities used by the google-workspace-cli (gws) command-line tool, and can be used independently for programmatic access.

Dynamic Discovery — this library fetches Google's Discovery Documents at runtime rather than relying on generated client crates. When Google adds or updates an API endpoint, your code picks it up automatically.

Modules Copy Chapter

Usage Copy Chapter

use google_workspace::discovery::fetch_discovery_document;
use google_workspace::services::resolve_service;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let (api, version) = resolve_service("drive").unwrap();
    let doc = fetch_discovery_document(api, version, None).await?;

    println!("{} {} — {} resources",
        doc.name, doc.version,
        doc.resources.len(),
    );
    Ok(())
}

License Copy Chapter

Apache-2.0 — see LICENSE.

File: docs/CODE_OF_CONDUCT.md Copy Chapter

Code of Conduct

Our Pledge Copy Chapter

In the interest of fostering an open and welcoming environment, we as
contributors and maintainers pledge to making participation in our project and
our community a harassment-free experience for everyone, regardless of age, body
size, disability, ethnicity, gender identity and expression, level of
experience, education, socio-economic status, nationality, personal appearance,
race, religion, or sexual identity and orientation.

Our Standards Copy Chapter

Examples of behavior that contributes to creating a positive environment
include:

• Using welcoming and inclusive language
• Being respectful of differing viewpoints and experiences
• Gracefully accepting constructive criticism
• Focusing on what is best for the community
• Showing empathy towards other community members

Examples of unacceptable behavior by participants include:

• The use of sexualized language or imagery and unwelcome sexual attention or
  advances
• Trolling, insulting/derogatory comments, and personal or political attacks
• Public or private harassment
• Publishing others' private information, such as a physical or electronic
  address, without explicit permission
• Other conduct which could reasonably be considered inappropriate in a
  professional setting

Our Responsibilities Copy Chapter

Project maintainers are responsible for clarifying the standards of acceptable
behavior and are expected to take appropriate and fair corrective action in
response to any instances of unacceptable behavior.

Project maintainers have the right and responsibility to remove, edit, or reject
comments, commits, code, wiki edits, issues, and other contributions that are
not aligned to this Code of Conduct, or to ban temporarily or permanently any
contributor for other behaviors that they deem inappropriate, threatening,
offensive, or harmful.

Scope Copy Chapter

This Code of Conduct applies both within project spaces and in public spaces
when an individual is representing the project or its community. Examples of
representing a project or community include using an official project e-mail
address, posting via an official social media account, or acting as an appointed
representative at an online or offline event. Representation of a project may be
further defined and clarified by project maintainers.

This Code of Conduct also applies outside the project spaces when the Project
Steward has a reasonable belief that an individual's behavior may have a
negative impact on the project or its community.

Conflict Resolution Copy Chapter

We do not believe that all conflict is bad; healthy debate and disagreement
often yield positive results. However, it is never okay to be disrespectful or
to engage in behavior that violates the project’s code of conduct.

If you see someone violating the code of conduct, you are encouraged to address
the behavior directly with those involved. Many issues can be resolved quickly
and easily, and this gives people more control over the outcome of their
dispute. If you are unable to resolve the matter for any reason, or if the
behavior is threatening or harassing, report it. We are dedicated to providing
an environment where participants feel welcome and safe.

Reports should be directed to the Project Maintainers ([email protected]). It is the Project Steward’s duty to
receive and address reported violations of the code of conduct. They will then
work with a committee consisting of representatives from the Open Source
Programs Office and the Google Open Source Strategy team. If for any reason you
are uncomfortable reaching out to the Project Steward, please email
[email protected].

We will investigate every complaint, but you may not receive a direct response.
We will use our discretion in determining when and how to follow up on reported
incidents, which may range from not taking action to permanent expulsion from
the project and project-sponsored spaces. We will notify the accused of the
report and provide them an opportunity to discuss it before any action is taken.
The identity of the reporter will be omitted from the details of the report
supplied to the accused. In potentially harmful situations, such as ongoing
harassment or threats to anyone's safety, we may take action without notice.

Attribution Copy Chapter

This Code of Conduct is adapted from the Contributor Covenant, version 1.4,
available at
https://www.contributor-covenant.org/version/1/4/code-of-conduct.html

File: docs/CONTRIBUTING.md Copy Chapter

How to contribute

We'd love to accept your patches and contributions to this project.

Before you begin Copy Chapter

Sign our Contributor License Agreement Copy Section

Contributions to this project must be accompanied by a
Contributor License Agreement (CLA).
You (or your employer) retain the copyright to your contribution; this simply
gives us permission to use and redistribute your contributions as part of the
project.

If you or your current employer have already signed the Google CLA (even if it
was for a different project), you probably don't need to do it again.

Visit https://cla.developers.google.com/ to see your current agreements or to
sign a new one.

Review our community guidelines Copy Section

This project follows
Google's Open Source Community Guidelines.

Contribution process Copy Chapter

Code reviews Copy Section

All submissions, including submissions by project members, require review. We
use GitHub pull requests for this purpose. Consult
GitHub Help for more
information on using pull requests.

Updating CI Smoketest Credentials Copy Section

If the OAuth refresh token used in the GitHub Actions smoketest expires or needs additional scopes, you can generate a new one and update the repository secret using the GitHub CLI (gh).

1. Set the credentials file path to output plaintext JSON:

   bash Copy

   export GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE=smoketest-creds.json

2. Authenticate with the required scopes:

   bash Copy

   cargo run -- auth login --scopes https://www.googleapis.com/auth/drive,https://www.googleapis.com/auth/gmail.readonly,https://www.googleapis.com/auth/calendar.readonly,https://www.googleapis.com/auth/presentations.readonly,https://www.googleapis.com/auth/tasks.readonly

3. Export and set the GitHub actions secret:

   bash Copy

   cargo run --quiet -- auth export --unmasked | base64 | gh secret set GOOGLE_CREDENTIALS_JSON

4. Clean up:

   bash Copy

   rm smoketest-creds.json
   unset GOOGLE_WORKSPACE_CLI_CREDENTIALS_FILE

Development Patterns Copy Chapter

Changesets Copy Section

Every PR must include a changeset file at .changeset/<descriptive-name>.md:

---
"@googleworkspace/cli": patch
---

Brief description of the change

Use patch for fixes/chores, minor for new features, major for breaking changes.

Input Validation & URL Safety Copy Section

This CLI is designed to be invoked by AI/LLM agents, so all user-supplied inputs must be treated as potentially adversarial. See AGENTS.md for the full reference. The key rules are:

Testing Expectations Copy Section

• All new validation logic must include both happy-path and error-path tests
• Tests that modify the process CWD must use #[serial] from serial_test
• Tempdir paths should be canonicalized before use to handle macOS /var → /private/var symlinks
• Run the full suite before submitting: cargo test && cargo clippy -- -D warnings

File: docs/skills.md Copy Chapter

Skills Index

Auto-generated by gws generate-skills. Do not edit manually.

Services Copy Chapter

Core Google Workspace API skills.

Helpers Copy Chapter

Shortcut commands for common operations.

Personas Copy Chapter

Role-based skill bundles.

Recipes Copy Chapter

Multi-step task sequences with real commands.