메뉴
Schedule one-time and recurring tasks with optional pre-check scripts
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
Evaluate whether a principal is authorized to request a lookup, action, or disclosure using the principal registry, action classes, group authorization, and outbound policy.
Apply recipient and outbound safety checks before sending email, messages, uploads, webhooks, or remote writes.
Search, fetch, and synthesize public information with citations while treating external inputs as untrusted.
Browse websites interactively — open pages, click elements, fill forms, take screenshots, extract data
Create, organize, and manage files and structured content in the workspace
Search the web, cross-reference sources, and produce cited findings
SOC 직업 분류 기준
| name | scheduling |
| description | Schedule one-time and recurring tasks with optional pre-check scripts |
| version | 1.0.0 |
| tools | ["schedule_task","list_tasks","pause_task","resume_task","cancel_task"] |
| triggers | ["remind me","schedule","every day","every week","check regularly"] |
Schedule tasks that run as full agent invocations on a cron schedule, interval, or one-time.
schedule_type: "cron", schedule_value: "0 9 * * 1" (Mondays at 9am)schedule_type: "interval", schedule_value: "3600000" (every hour in ms)schedule_type: "once", schedule_value: "2026-04-01T09:00:00Z" (ISO timestamp)For recurring tasks, add a script that runs before the agent wakes up. This saves API credits by only invoking the agent when action is needed.
# Script prints JSON to stdout
# { "wakeAgent": true/false, "data": {...} }
If wakeAgent: false, the agent sleeps until the next run. If true, the agent receives the script's data alongside the prompt.