verifier
Cheap gate before accepting another agent's diff - does it match the task (scope, completeness, obvious breakage)? Returns PASS/FAIL with reasons. NOT a code review - it catches "did the wrong thing"; real reviews go to reviewer.
$ npx -y skills add AqueGen/model-routing --agent claude-codeShips 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.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Cheap gate before accepting another agent's diff - does it match the task (scope, completeness, obvious breakage)? Returns PASS/FAIL with reasons. NOT a code review - it catches "did the wrong thing"; real reviews go to reviewer.
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.
Repo: AqueGen/model-routing
Other agents on model-routing.
- e2e-runner
Drives browser/E2E scenarios and interprets test failures (product bug vs test bug vs flake). Costlier than test-runner - use test-runner for plain run-and-report.
Open agent - implementer
Implements one well-defined task from an approved plan or spec. Needs a self-contained task description; not for exploratory or ambiguous work. Pinned to sonnet - dispatch with model=opus for multi-file, architectural, or subtle work.
Open agent - reviewer
Reviews a diff for correctness bugs and design problems before commit/PR. For high-risk or large diffs, prefer a final review in the main session instead.
Open agent - scout
Read-only codebase explorer. Use for "where is X", "how does Y work", "which files touch Z" - returns conclusions with file:line refs, never file dumps. Never modifies anything.
Open agent - 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.
Open agent