DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run inbox triage on a daily schedule with Agents Office

Set a routine in the Emails department so the office sorts the inbox at a fixed time each weekday.

Credentials. A scheduled routine can read connected mail on its own clock, so check what it may touch and use the needs-my-OK step where offered.

Who it is forA busy professional who checks email first thing each morning and wants a short list of what needs a reply before starting work.

The problemTriaging the inbox by hand every morning eats time, and important messages get missed when the day starts.

The outcomeA routine that runs on the office's clock and reports what needs you, shown as SCHEDULED in the Task Status panel.

What you need first

  • macOS or Linux (Windows can use the npm commands directly, since ./setup is Bash only)
  • Node.js 20+
  • git
  • Claude Code logged in with your Claude account, or an ANTHROPIC_API_KEY (tool use needs the Claude Code login)

Steps

  1. Complete the setup in the first use case so the office is running at http://localhost:4520.
  2. In the task bar, choose the Emails department and type a line such as: every weekday at 8am, triage the inbox and tell me what needs me.
  3. Check the hint line, which reads the schedule back, then press Add.
  4. Find the SCHEDULED chip in the Task Status panel to confirm the countdown.
  5. Use the lead's chat to pause, resume, run now or delete the routine by name.

Prompt for your agent

Use the agents-office repo at https://github.com/ajsahni/agents-office running at http://localhost:4520. Create a routine in the Emails department for '<schedule and task>' and report the routine's name and next run time. Verify it appears as SCHEDULED in the Task Status panel.

Caveat. Routines run on this machine's clock, so the office must be running at the scheduled time for the routine to fire.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page