google-tasks

google-tasks is a skill for Claude Code, Codex from clearsmog/claude-skills. It costs 38 tokens per session (405 once invoked), scanned A, original, MIT.

A command-line tool for managing Google Tasks, Google's service for personal to-do lists and reminders.

In plain words
What is it for?
It helps list task lists and tasks, add due dates and notes, update task details, mark tasks complete, delete tasks, and clear completed tasks.
Why use it?
It lets you view and change tasks from the terminal instead of managing them manually in the web or app interface.

Skill for Claude CodeCodex

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

Good fit It helps list task lists and tasks, add due dates and notes, update task details, mark tasks complete, delete tasks, and clear completed tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/clearsmog/claude-skills/google-tasks
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 clearsmog/claude-skills --skill google-tasks
Clone the repo
git clone --depth 1 https://github.com/clearsmog/claude-skills

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/clearsmog/claude-skills/google-tasks"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/google-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 405 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 $0.00038 $0.00405
Opus 5 $0.00019 $0.00202
Sonnet 5 $0.00008 $0.00081
Haiku 4.5 $0.00004 $0.00040

Measured 9d ago against content hash 3ebc97f8e305, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

google-tasks 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 9d 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.

google-tasks/SKILL.md · 41 lines

What it actually says

Google Tasks CLI

gtasks is globally installed at ~/.local/bin/gtasks. Use it via Bash to manage the user's Google Tasks.

Source: ~/Developer/Tools/GoogleTasks/ Reinstall after edits: uv tool install ~/Developer/Tools/GoogleTasks --force

Commands

gtasks lists                                          # Show all task lists
gtasks list [LIST_NAME]                               # Show tasks in a list (default if omitted)
gtasks list [LIST_NAME] --all                         # Include completed tasks
gtasks add "TITLE" [-l LIST] [-n NOTES] [-d YYYY-MM-DD]   # Create a task
gtasks update TASK_ID [-l LIST] [-t TITLE] [-n NOTES] [-d YYYY-MM-DD]  # Update a task
gtasks complete TASK_ID [TASK_ID...] [-l LIST]         # Mark task(s) done
gtasks delete TASK_ID [TASK_ID...] [-l LIST] [--yes]   # Delete task(s)
gtasks clear [-l LIST] [--yes]                        # Remove all completed tasks

Task Lists

  • ⏰ Urgent
  • 🎯 Important
  • 🎉 Fun
  • ✅ To-Do List
  • Old Google Keep reminders

Usage Notes

  • Always run gtasks list first to get task IDs before updating/completing/deleting.
  • List names with emoji must be quoted: gtasks list "⏰ Urgent"
  • Multiple task IDs can be passed to complete and delete.
  • Always confirm with the user before deleting tasks.
  • The --yes flag skips confirmation prompts (use only when user explicitly says to skip).
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. 9d ago First seen · 41 lines · 38 tokens per session scan A 3ebc97f8e305

Subscribe to this mod's changes

google-tasks is a skill published in the GitHub repository clearsmog/claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 405 once invoked, about $0.0002 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 2026-08-31.