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.
npx skills add phamviet86/google-task-mcp --skill google-tasksgit clone --depth 1 https://github.com/phamviet86/google-task-mcpWrote 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.
[](https://agentmods.dev/skills/phamviet86/google-task-mcp/google-tasks)<a href="https://agentmods.dev/skills/phamviet86/google-task-mcp/google-tasks"><img src="https://agentmods.dev/badge/skills/phamviet86/google-task-mcp/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.
<a href="https://agentmods.dev/skills/phamviet86/google-task-mcp/google-tasks"><img src="https://agentmods.dev/badge/skills/phamviet86/google-task-mcp/google-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00497 |
| Opus 5 | $0.00013 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Tasks MCP usage
Use the configured local google-tasks-mcp server to work with the user's Google Tasks. It exposes
exactly 14 tools: list_task_lists, get_task_list, create_task_list, update_task_list,
delete_task_list, list_tasks, get_task, create_task, update_task, complete_task,
reopen_task, move_task, delete_task, and clear_completed_tasks.
Work safely
Resolve a human-readable task-list name with list_task_lists, then read the list or task before
changing an existing resource when current state matters. Use the returned IDs. After an uncertain
write result or API error, re-read the affected resource before retrying; do not blindly repeat a
write.
Creating a list or task is additive and has a non-destructive annotation, but still needs the
user's request. Renaming, updating, moving, completing, and reopening affect existing user data;
treat their conservative destructive-risk annotations as a prompt to confirm the intended target
and outcome. The user's exact authorization for that named action is sufficient to perform it.
For delete_task_list, delete_task, or clear_completed_tasks, require explicit authorization
for the named target and then provide confirm: true; reuse exact existing authorization in the
current request, otherwise ask. Clearing completed tasks hides completed tasks through Google's
clear operation; it is not a substitute for a general deletion preview.
Preserve patch intent
For update_task, omit every field the user wants left unchanged. Send explicit null only to
clear notes or due; null for title or status is invalid. A due value may be YYYY-MM-DD
or RFC 3339, but Google Tasks retains only the date. Use complete_task and reopen_task for
clear status intent rather than combining unrelated updates.
Use list_tasks pagination and filters deliberately. To inspect completed tasks as shown in
Google's first-party clients, request both show_completed: true and show_hidden: true. Keep
task titles and notes within the server's validation limits, and never request or expose OAuth
credentials while handling task work.
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.
- today First seen · 40 lines · 25 tokens per session scan A 9ce8c1b1f124
google-tasks is a skill published in the GitHub repository phamviet86/google-task-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 497 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.
Other skills, from other repositories
create-milestone
Create a GitHub milestone for an upcoming release. Suggests the next version based on the latest release, gathers all merged PRs and closed issues since that release, presents a draft with two tables (Issues and PRs) for user approval, then creates the milestone and assigns all approved items.
gh-issues
Triage GitHub issues, select safe candidates, implement focused fixes, open pull requests, and address actionable review feedback.
document-to-action-items
Turn documents, notes, transcripts, and meeting records into traceable action items, decisions, owners, deadlines, and follow-ups without inventing missing commitments.
github
Use GitHub CLI for repositories, issues, pull requests, reviews, CI runs, releases, and structured GitHub API queries.
kill-the-standup
Reads yesterday's Linear issues and GitHub commits for the authenticated user, formats a standup update (done / doing / blockers), and posts it to Slack. Use when asked to write a standup, generate a standup update, post to the standup channel, summarize yesterday's work, or automate the daily standup. Trigger when a…
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.