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

How to rename and retarget agents with Claude Code with Agents Office

Describe a new role in plain words and let Claude Code update the agent roster for you.

Who it is forAn operator who wants the office's 35 seats to match their real work, such as turning inbound sales seats into wholesale account seats.

The problemEditing the agents file by hand is slow, and mistakes in ids or departments break the office.

The outcomeA local roster file with your renamed agents and retargeted roles, validated and loaded after a restart.

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. Run cd agents-office and then claude to open Claude Code in the folder.
  2. Say what you want, for example: Rename the Newsletter agent to PODCAST NOTES and say what it does.
  3. Let Claude Code write the changes to office.agents.local.json and validate them with npm run check.
  4. Restart the office with npm start and open http://localhost:4520 to see the new names at the desks.
  5. Keep the local file out of git, since it is ignored and git pull will not overwrite it.

Prompt for your agent

In the agents-office repo at https://github.com/ajsahni/agents-office, rename the agent <current name> to <new name> and rewrite its role for <new purpose>. Run npm run check and report any validation errors. Verify the new name appears on its desk after npm start.

Caveat. Edits to id, department or lead are ignored and the server says so at start, so only change names, roles, what agents do and their tools.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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