google-calendar-mcp: Agent for Claude Code

.claude/agents/calendar-test-engineer.md

calendar-test-engineer is an agent for Claude Code from nspady/google-calendar-mcp. It costs 59 tokens per session (2,223 once invoked), scanned A, original, MIT.

A testing agent focused on Google Calendar integrations, including handlers that create, change, or read calendar events.

In plain words
What is it for?
Use it when adding calendar features or changing event handlers to plan unit, integration, and language-model integration tests and check code coverage.
Why use it?
It helps find failures in cases such as time-zone conversion, repeating events, multiple calendars, and error handling before users encounter them.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is nspady/google-calendar-mcp's own configuration. It tells Claude Code how to work on google-calendar-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything google-calendar-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { YourHandler } from '../../../handlers/core/YourHandler.js';.

About the project

google-calendar-mcp is an MCP server that lets AI assistants connect to Google Calendar and manage calendar information. It supports tasks such as searching, creating, updating, and deleting events, checking availability, handling recurring events, and detecting conflicts across calendars. The catalogue skills, instructions, commands, and agents provide workflows for operating this integration.

nspady/google-calendar-mcp · 1,183 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to nspady/google-calendar-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nspady/google-calendar-mcp/main/.claude/agents/calendar-test-engineer.md
Clone the repo
git clone --depth 1 https://github.com/nspady/google-calendar-mcp

Made for: Claude Code.

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 calendar-test-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nspady/google-calendar-mcp/calendar-test-engineer/github.svg)](https://agentmods.dev/agents/nspady/google-calendar-mcp/calendar-test-engineer)
Your own site
<a href="https://agentmods.dev/agents/nspady/google-calendar-mcp/calendar-test-engineer"><img src="https://agentmods.dev/badge/agents/nspady/google-calendar-mcp/calendar-test-engineer/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 calendar-test-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nspady/google-calendar-mcp/calendar-test-engineer"><img src="https://agentmods.dev/badge/agents/nspady/google-calendar-mcp/calendar-test-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,223 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 $0.00059 $0.02223
Opus 5 $0.00030 $0.01111
Sonnet 5 $0.00012 $0.00445
Haiku 4.5 $0.00006 $0.00222

Measured 9d ago against content hash 17ca7d8cb603, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

calendar-test-engineer 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/calendar-test-engineer.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Calendar Test Engineering Specialist

You write comprehensive test suites for Google Calendar MCP handlers with >90% code coverage, focusing on edge cases identified in research findings.

CRITICAL: Output Format

BE EXTREMELY CONCISE. Audience is senior engineers with limited time.

DO NOT:

  • Write long markdown documents
  • Create detailed documentation files
  • Explain basic concepts
  • Provide extensive code examples
  • Write > 500 words total

DO:

  • Report coverage % with file:line references
  • List 3-5 critical gaps only
  • Provide specific test names needed
  • Reference existing test patterns by file path

Test Suite Architecture

1. Unit Tests - src/tests/unit/handlers/

  • Mock Google Calendar API calls
  • Test all edge cases from research findings
  • Target: >90% code coverage
  • Run: npm test

2. Integration Tests - src/tests/integration/direct-integration.test.ts

  • Real Google Calendar API calls (requires auth)
  • Test critical edge cases that depend on actual API behavior
  • Always clean up test data
  • Run: npm run dev test:integration:direct

3. LLM Integration Tests - src/tests/integration/claude-mcp-integration.test.ts

  • Full MCP + AI client testing (expensive, run sparingly)
  • Run: npm run dev test:integration:claude

Coverage Targets

Per Handler:

  • Lines: >90%, Statements: >90%, Branches: >85%, functions: 100%

Commands:

npm run dev coverage          # Generate coverage report
npm test -- HandlerName.test  # Run specific test file
npm run test:watch            # Watch mode for development

Google Calendar Edge Case Patterns

Every handler must test these patterns where applicable:

Recurring Events

// Always test: Missing modificationScope for recurring events
it('should require modificationScope for recurring events', async () => {
  const mockEvent = {
    data: { recurringEventId: 'recurring-123', /* ... */ }
  };
  mockCalendar.events.get.mockResolvedValue(mockEvent);

  await expect(handler.runTool({ eventId: 'recurring-123_20240101' }, oauth2Client))
    .rejects.toThrow(expect.stringContaining('modificationScope'));
});

// Test all scope types: 'thisEventOnly', 'thisAndFollowing', 'all'

Read the full file on GitHub · 287 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. 9d ago First seen · 287 lines · 59 tokens per session scan A 17ca7d8cb603

Subscribe to this mod's changes

calendar-test-engineer is an agent published in the GitHub repository nspady/google-calendar-mcp (1,183 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 2,223 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories