google-task-mcp AGENTS.md

google-task-mcp AGENTS.md is an instructions file for Codex, OpenCode from phamviet86/google-task-mcp. It costs 598 tokens per session, scanned A, original, MIT.

Repository instructions for a local, standard-input/output MCP server connected to one authenticated Google Tasks account. They define safe handling of credentials and task data.

In plain words
What is it for?
Use them when developing, testing, authenticating, or modifying the google-task-mcp project.
Why use it?
They prevent accidental exposure of OAuth secrets or real task content and require confirmation for destructive task actions.

Instructions file for CodexOpenCode

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 instructions/phamviet86/google-task-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/phamviet86/google-task-mcp

Made for: Codex, OpenCode.

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-task-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/phamviet86/google-task-mcp/agents-md.svg)](https://agentmods.dev/instructions/phamviet86/google-task-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/phamviet86/google-task-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/phamviet86/google-task-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 598 This file is loaded in full into every session.
When invoked 598 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00598 $0.00598
Opus 5 $0.00299 $0.00299
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured yesterday against content hash 40b43a49ed5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

google-task-mcp AGENTS.md 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.

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent contract

This repository is a local, stdio-only MCP server for one authenticated Google Tasks account. Keep the repository name google-task-mcp, the console commands google-tasks-mcp and google-tasks-mcp-auth, and the unique distribution name phamviet-google-tasks-mcp distinct.

Operating rules

  • Never read, create, commit, print, or request OAuth client secrets, authorization codes, refresh tokens, token files, real task content, or unredacted client configuration during ordinary work. A live authenticated read is allowed only when a maintainer explicitly authorizes it and provides a dedicated non-production Google account containing only test data. Otherwise do not invoke a Google tool and record the authenticated-read check as NOT_VERIFIED.
  • Treat Google Tasks as external user data. In a maintainer-authorized interaction, read before modifying when context matters; ask for explicit user confirmation before delete_task_list, delete_task, or clear_completed_tasks.
  • Do not represent MCP initialization or tool discovery as an authentication test. Discovery works without credentials; a real tool call requires a valid token.
  • Preserve stdio-only operation. Do not add a listener, database, background service, sync job, or webhook without an explicit architecture decision.
  • Use absolute executable and token paths in client examples. Keep local tokens outside the checkout.
  • macOS and Linux are the current supported release platforms. Do not claim Windows support until permission handling and end-to-end operation are verified.

Change contract

When behavior changes, keep README.md, README.vi.md, docs/release-deployment.md, and tests in sync with the runtime schema. Preserve the 14-tool public contract unless a versioned compatibility decision explicitly changes it. Maintain the difference between omitted update fields and explicit null for clearing notes or due.

Before proposing a release, follow the release and deployment guide, run the configured format, lint, type, and test checks; build the artifact; install it in a clean dedicated virtual environment; and run the machine-actionable verifiers:

Read the full file on GitHub · 47 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 · 47 lines · 598 tokens per session scan A 40b43a49ed5b

Subscribe to this mod's changes

google-task-mcp AGENTS.md is an instructions file published in the GitHub repository phamviet86/google-task-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 598 tokens to every session, about $0.0030 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 2026-09-04.