Skip to content

test-runner

Runs tests, builds, and linters; reports compactly. Mechanical run-and-report only. Do NOT use when failures need interpretation or fixing - that is e2e-runner or the main session.

From plugin
36 skills6 agents1 commands2 hooks
shell
$ npx -y skills add AqueGen/model-routing --agent claude-code

Ships with model-routing. Installing the plugin gets this agent.

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this agent.

Runs tests, builds, and linters; reports compactly. Mechanical run-and-report only. Do NOT use when failures need interpretation or fixing - that is e2e-runner or the main session.
Ships withmodel-routing

Tiered model routing for Claude Code token economy: **the strongest model thinks, cheaper models grind.** Planning and architecture stay in your main session on the best model you have.

Get the whole plugin, auto-invoked