google-calendar

google-calendar is a skill for Claude Code from team-attention/plugins-for-claude-natives. It costs 51 tokens per session (1,801 once invoked), scanned B, original, MIT.

A tool for viewing and managing events in one or more Google Calendars, including work and personal accounts. It supports reading, creating, editing, deleting, and checking for scheduling conflicts.

In plain words
What is it for?
Use it to view today’s or this week’s schedule, find upcoming meetings, create or change events, cancel events, and compare calendars for conflicts.
Why use it?
It removes the need to check several calendars separately and helps prevent missed meetings, duplicate bookings, and conflicting events.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents.

Part of the google-calendar plugin — 1 skill shipped together

Good fit Use it to view today’s or this week’s schedule, find upcoming meetings, create or change events, cancel events, and compare calendars for conflicts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/team-attention/plugins-for-claude-natives/google-calendar
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 team-attention/plugins-for-claude-natives --skill google-calendar
Clone the repo
git clone --depth 1 https://github.com/team-attention/plugins-for-claude-natives

Made for: Claude Code.

Or install google-calendar, the plugin that ships this one along with the rest of its 1 skill.

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-calendar

README.md
[![agentmods](https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/google-calendar/github.svg)](https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/google-calendar)
Your own site
<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/google-calendar"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/google-calendar/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-calendar

Your own site · 80×15
<a href="https://agentmods.dev/skills/team-attention/plugins-for-claude-natives/google-calendar"><img src="https://agentmods.dev/badge/skills/team-attention/plugins-for-claude-natives/google-calendar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,801 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00051 $0.01801
Opus 5 $0.00026 $0.00901
Sonnet 5 $0.00010 $0.00360
Haiku 4.5 $0.00005 $0.00180

Measured 12d ago against content hash 8810156ac9fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

google-calendar scanned grade B with 1 finding 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/calendar_client.py, scripts/fetch_events.py, scripts/manage_events.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls .claude/skills/google-calendar/accounts/
plugins/google-calendar/skills/google-calendar/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Calendar Sync

Overview

여러 Google 계정(회사, 개인 등)의 캘린더를 한 번에 조회하여 통합된 일정을 제공한다.

  • 사전 인증된 refresh token 사용 (매번 로그인 불필요)
  • Subagent 병렬 실행으로 빠른 조회
  • 계정 간 일정 충돌 감지

트리거 조건

조회

  • "오늘 일정", "이번 주 일정 알려줘"
  • "캘린더 확인", "스케줄 뭐야"
  • "다음 미팅", "내일 뭐 있어"
  • "일정 충돌 확인해줘"

생성

  • "새 일정 만들어줘", "미팅 추가해줘"
  • "내일 3시에 회의 잡아줘"
  • "다음 주 월요일 팀 미팅 생성"

수정

  • "일정 시간 변경해줘", "미팅 시간 바꿔줘"
  • "sync 미팅 14시 21분으로 변경"
  • "회의 제목 수정해줘"

삭제

  • "일정 삭제해줘", "미팅 취소해줘"
  • "이벤트 지워줘"

사전 요구사항

1. Google Cloud 프로젝트 설정

  1. Google Cloud Console에서 프로젝트 생성
  2. Calendar API 활성화
  3. OAuth 2.0 Client ID 생성 (Desktop 유형)
  4. credentials.json 다운로드 → references/credentials.json에 저장

2. 계정별 인증 (최초 1회)

# 회사 계정
uv run python .claude/skills/google-calendar/scripts/setup_auth.py --account work

# 개인 계정
uv run python .claude/skills/google-calendar/scripts/setup_auth.py --account personal

브라우저에서 Google 로그인 → refresh token이 accounts/{name}.json에 저장됨

워크플로우

1. 등록된 계정 확인

ls .claude/skills/google-calendar/accounts/
# → work.json, personal.json

2. Subagent 병렬 실행

각 계정별로 Task 도구를 병렬로 호출:

# 병렬 실행 - 단일 메시지에 여러 Task 호출
Task(subagent_type="general-purpose", prompt="fetch calendar for work account")
Task(subagent_type="general-purpose", prompt="fetch calendar for personal account")

각 subagent는 다음을 실행:

uv run python .claude/skills/google-calendar/scripts/fetch_events.py \
  --account {account_name} \
  --days 7

3. 결과 통합

  • 모든 계정의 이벤트를 시간순 정렬
  • 동일 시간대 이벤트 = 충돌로 표시
  • 계정별 색상/아이콘 구분

출력 형식

📅 2026-01-06 (월) 일정

[09:00-10:00] 🔵 팀 스탠드업 (work)
[10:00-11:30] 🟢 치과 예약 (personal)
[14:00-15:00] 🔵 고객 미팅 - 삼양 (work)
              ⚠️ 충돌: 개인 일정과 겹침
[14:00-14:30] 🟢 은행 방문 (personal)

📊 오늘 총 4개 일정 (work: 2, personal: 2)
   ⚠️ 1건 충돌

실행 예시

사용자: "이번 주 일정 알려줘"

1. accounts/ 폴더 확인
   └── 등록된 계정: work, personal

2. Subagent 병렬 실행
   ├── Task: work 계정 이벤트 조회
   └── Task: personal 계정 이벤트 조회

3. 결과 수집 (각 subagent 완료 대기)
   ├── work: 8개 이벤트
   └── personal: 3개 이벤트

4. 통합 및 정렬
   └── 11개 이벤트, 2건 충돌 감지

5. 출력
   └── 일별로 그룹화하여 표시

Read the full file on GitHub · 231 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 231 lines · 51 tokens per session scan B 8810156ac9fc

Subscribe to this mod's changes

google-calendar is a skill published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,801 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories