DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to let an agent route its next work phase via skill with Agent Router

Link the model-router skill so an agent can route the next phase of your work through the router.

Who it is forA developer already working inside Claude Code, Codex, or Cursor who wants the agent to hand off the next phase, such as implementation, to a better-suited agent.

The problemAn agent working on a plan has no built-in way to send the next phase to a different agent or model that fits the work and quota.

The outcomeThe agent can route the next phase by using the linked model-router skill, with the choice made by the router.

What you need first

  • Node.js 20 or newer
  • A TypeSafe API key, since routing always calls TypeSafe
  • At least one agent CLI you are logged in to: agent (Cursor), claude (Claude Code), codex, or opencode
  • Herdr, for launching agents without --dry-run
  • A config file with your accounts in the model-router home folder

Steps

  1. Complete the setup steps for installing, building, and configuring the router.
  2. Run ln -s "$PWD/skills/model-router" ~/.claude/skills/model-router for Claude Code, and the matching links for Codex or Cursor.
  3. Start a new session in the agent and ask it to route the next phase of a plan.
  4. Check that the agent runs the router rather than doing the phase itself.

Prompt for your agent

Using the model-router skill from the agent-router repo, route the next phase of the plan at <plan path> and report which agent, model, and effort the router selected. Verify that the router decision card appears in the output before any work starts.

Caveat. The README says the router routes one phase per task and does not answer the question itself, so the launched agent still does the work.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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