google-tasks-setup

google-tasks-setup is a skill for Claude Code, Codex from phamviet86/google-task-mcp. It costs 29 tokens per session (914 once invoked), scanned A, original, MIT.

A setup guide for a local Google Tasks service, including browser-based authorization for one Google account. Google Tasks is Google's task-list and reminder service.

In plain words
What is it for?
Use it when installing, authorizing, updating, or checking the local Google Tasks connection and its MCP client configuration.
Why use it?
It provides a defined way to install the service, authorize access, and diagnose configuration without guessing executable paths. The local service does not keep a task cache or open a network port.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when installing, authorizing, updating, or checking the local Google Tasks connection and its MCP client configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phamviet86/google-task-mcp/google-tasks-setup
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.

Any agent
npx skills add phamviet86/google-task-mcp --skill google-tasks-setup
Clone the repo
git clone --depth 1 https://github.com/phamviet86/google-task-mcp

Made for: Claude Code, Codex.

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-tasks-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/phamviet86/google-task-mcp/google-tasks-setup/github.svg)](https://agentmods.dev/skills/phamviet86/google-task-mcp/google-tasks-setup)
Your own site
<a href="https://agentmods.dev/skills/phamviet86/google-task-mcp/google-tasks-setup"><img src="https://agentmods.dev/badge/skills/phamviet86/google-task-mcp/google-tasks-setup/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-tasks-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/phamviet86/google-task-mcp/google-tasks-setup"><img src="https://agentmods.dev/badge/skills/phamviet86/google-task-mcp/google-tasks-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 914 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00029 $0.00914
Opus 5 $0.00015 $0.00457
Sonnet 5 $0.00006 $0.00183
Haiku 4.5 $0.00003 $0.00091

Measured today against content hash f9a31971e37b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade A, and why

google-tasks-setup 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 today.

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.

src/google_tasks_mcp/skills/google-tasks-setup/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Tasks MCP setup

Use this skill when a user wants to install, configure, authorize, or diagnose the local Google Tasks MCP server. It is a stdio server for one local Google account and keeps no local task cache. The server opens no network port; the authorization helper may use a temporary local loopback callback while the user completes browser consent.

Start locally

For the installed 0.4.0 release or a later release, read this skill's references/runtime.json before running a command. Use its absolute server field:

/absolute/path/from/runtime.json/google-tasks-mcp doctor

If the installed skills need repair or update, retain their current skills root and use install-skills --check --dest CURRENT_ROOT; after review, use --replace with that same destination when needed. It accepts --dry-run without writes. The installed references/runtime.json holds nonsecret identifiers for the matching distribution and version plus absolute python, server, and auth paths. Use the absolute paths in the MCP client configuration; do not guess paths or resolve a virtual-environment Python symlink.

doctor only stats the configured token path and its permissions. Its authentication and mcp_discovery results remain unverified; a token file or successful tool discovery never proves that Google authorization works.

Published v0.3.1 does not provide install-skills or doctor. Before installing v0.4.0, verify that its GitHub Release provides the wheel, source archive, and SHA256SUMS; do not treat a source branch or tag as a published release.

Configure Google and OAuth

Reuse the user's selected existing Google account, Cloud project, OAuth configuration, and token location. Preserve the server's Google Tasks scope and the configured GOOGLE_TOKEN_FILE; use an absolute protected path outside a checkout. Never ask for, copy, print, or store OAuth JSON contents, authorization codes, refresh tokens, token files, or task data in chat or manual inspection. Passing the selected local JSON path to the authorization helper is expected: the helper reads it and persists the authorized-user token locally.

Read the full file on GitHub · 79 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. today First seen · 79 lines · 29 tokens per session scan A f9a31971e37b

Subscribe to this mod's changes

google-tasks-setup is a skill published in the GitHub repository phamviet86/google-task-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 914 once invoked, about $0.0001 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 2026-09-14.