gws-shared

Shared instructions for using the gws command-line tool in a proxy-authenticated environment. They explain the required way to identify the user for each command and which normal login or installation steps to avoid.

In plain words
What is it for?
Running gws commands through the configured proxy, especially when acting on behalf of a specified user.
Why use it?
They prevent failed authentication and accidental changes to the customised setup.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/streakyc/googleworkspacecli/gws-shared
Any agent
npx skills add StreakYC/googleworkspacecli --skill gws-shared
Clone the repo
git clone --depth 1 https://github.com/StreakYC/googleworkspacecli

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,753 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.01753
Opus 5 $0.00010 $0.00877
Sonnet 5 $0.00004 $0.00351
Haiku 4.5 $0.00002 $0.00175

Measured yesterday against content hash 8e9fe5c691f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gws-shared 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 yesterday.

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.

skills/gws-shared/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gws — Shared Reference

This is a customized gws-shared for a headless, proxy-authenticated environment. The auth model below replaces the upstream gws auth login / service-account flow — do not follow auth instructions from upstream docs or --help output.

Installation

The gws binary is already installed and on $PATH. Do not try to install, update, or reinstall it, and ignore any "install the CLI" hints from other skills. Do not run gws generate-skills as it will overwrite our customized configurations.

Authentication

There is no interactive user and no service-account key file here, so the usual flows do not work and must not be attempted:

  • Do not run gws auth login, gws auth setup, or any gws auth ... command.
  • Do not set GOOGLE_APPLICATION_CREDENTIALS or point at a key.json.

Instead, authentication is handled transparently by a proxy. On every command you MUST pass --email=<address> naming the user you are acting on behalf of:

gws gmail +send [email protected] --to [email protected] --subject 'Hi' --body 'Hello' --draft

The gws wrapper forwards the request through the proxy, which swaps the --email=<address> you supply for that user's real OAuth token before the request reaches Google. You never see, request, or handle tokens yourself — you only ever name the acting user with --email.

  • Use the equals form --email=<address> (not --email <address>). Only the equals form is recognized; the space-separated form is treated as missing.
  • --email=<address> is required on every invocation, across all services (gmail, calendar, drive, …). This is the cross-surface convention for this environment.
  • The per-surface skill examples omit --email for brevity — add it to every real command you run.
  • Never ask for, print, or invent an OAuth token, API key, or credentials path — the proxy owns all of that.
  • If a command fails saying --email is required, add it. Do not fall back to gws auth login.

Read the full file on GitHub · 152 lines

Changes

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.

  1. yesterday First seen · 152 lines · 21 tokens per session scan A 8e9fe5c691f7

Subscribe to this mod's changes

gws-shared is a skill published in the GitHub repository StreakYC/googleworkspacecli (0 stars, last pushed 27d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,753 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens