google-cloud-auth

google-cloud-auth is a skill for Claude Code from VKirill/claude-lane-stack. It costs 104 tokens per session (2,818 once invoked), scanned C, original, MIT.

A reference guide for authenticating applications with Google APIs. It explains OAuth, service accounts, application default credentials, token refresh problems, and related library versions.

In plain words
What is it for?
Use it when connecting applications to services such as Google Search Console, Analytics, Tag Manager, YouTube, or Drive, either for users or server-to-server access.
Why use it?
It helps choose the right Google authentication method and diagnose expired, revoked, or unauthorized credentials.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Source of truth: [STACK_VERSIONS.md](../../STACK_VERSIONS.md) — verified 2026-06-11.

Part of the lane-stack plugin — 57 skills, 4 commands, 17 agents, 1 hook shipped together

Good fit Use it when connecting applications to services such as Google Search Console, Analytics, Tag Manager, YouTube, or Drive, either for users or server-to-server access.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/VKirill/claude-lane-stack
agentmods
npx agentmods add skills/vkirill/claude-lane-stack/google-cloud-auth

Made for: Claude Code.

Or install lane-stack, the plugin that ships this one along with the rest of its 57 skills, 4 commands, 17 agents, 1 hook.

Wrote 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.

agentmods badge for google-cloud-auth

README.md
[![agentmods](https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/google-cloud-auth/github.svg)](https://agentmods.dev/skills/vkirill/claude-lane-stack/google-cloud-auth)
Your own site
<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/google-cloud-auth"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/google-cloud-auth/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.

agentmods 80×15 button for google-cloud-auth

Your own site · 80×15
<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/google-cloud-auth"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/google-cloud-auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,818 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
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 5.1 $0.00104 $0.02818
Opus 5 $0.00052 $0.01409
Sonnet 5 $0.00021 $0.00564
Haiku 4.5 $0.00010 $0.00282

Measured 7d ago against content hash 0aeb0b648341, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

google-cloud-auth scanned grade C with 1 finding 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

ADC is the zero-config credential discovery chain used by all Google client libraries (`google-auth`, `googleapis`, `google-auth-library`). When code calls `google.auth.default()` or `new GoogleAuth()`, the library walks
plugins/lane-stack/skills/google/google-cloud-auth/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎯 Version Requirements (June 2026)

Primary pins:

  • google-auth-library (Node): 9.x
  • google-auth (Python): 2.x
  • Node.js: 24.x (Active LTS)
  • Python: 3.14.x

Source of truth: STACK_VERSIONS.md — verified 2026-06-11

Usage

Loaded automatically when its description matches the active task. This is the single source of truth for all Google API authentication patterns. Read the section you need, then follow the link to the relevant reference file.

Use this skill when

  • Setting up OAuth 2.0 Authorization Code flow (installed app or web app) for any Google API — GSC, GA4, GTM, YouTube, Drive
  • Configuring a Service Account for server-to-server (backend) access: creating SA, downloading key.json, granting access
  • Understanding Application Default Credentials (ADC) and GOOGLE_APPLICATION_CREDENTIALS env var discovery chain
  • Diagnosing invalid_grant, token_has_been_expired_or_revoked, or 401 Unauthorized on a previously working token
  • Choosing between OAuth user flow and Service Account for a given use case
  • Implementing offline access (access_type=offline) and prompt=consent to force a new refresh token
  • Configuring PKCE for installed apps or web apps that cannot store a client secret securely
  • Setting up domain-wide delegation (DWD) — impersonating G Suite users via a Service Account
  • Reviewing minimum scopes needed for a specific Google API (GSC readonly, GA4 readonly, GTM publish, YouTube, etc.)
  • Auditing OAuth consent screen configuration (redirect URIs, app verification, testing vs production mode)

Do not use this skill when

  • You need to make GA4 Data API calls — auth is covered in context; load google-analytics for request shape, quotas, and FilterExpression DSL
  • You need to query Google Search Console data — load google-search-console for dimensions, filters, and URL Inspection
  • You need GTM container / tag management — load google-tag-manager for resource hierarchy and CRUD operations
  • You need Yandex OAuth (Yandex Metrika, Direct, Webmaster) — different provider; load yandex-metrica, yandex-direct, or yandex-webmaster
  • You need general HTTP transport patterns (retries, backoff, connection pooling) — load httpx (Python) or nodejs

Read the full file on GitHub · 146 lines

Files

What ships with it

6 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.

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. 7d ago First seen · 146 lines · 104 tokens per session scan C 0aeb0b648341

Subscribe to this mod's changes

google-cloud-auth is a skill published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 2,818 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.