Claude Code plugin for token economy: the strongest model thinks, cheaper models grind. Pinned subagents (sonnet scout and implementer, haiku test-runner, opus reviewer), a routing skill, and a dispatch counter that measures what actually stayed off the session model.
Plugin Claude Code
Tiered model routing for token economy: the strongest model thinks, cheaper models grind. Ready-made subagents (sonnet scout, implementer and E2E runner, haiku surveyor, test-runner and verifier, opus reviewer) plus a routing skill and dispatch stats.
Agent
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.
Agent
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.
Agent
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.
Agent
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.
Agent
Read-only breadth sweeps over a codebase - enumerate, list, trace a chain end to end ("list every stage in order", "which files import X", "where does this pipeline end"). Returns the list or the ordering, never file dumps. Use scout instead when the answer needs judgement about what code does. Never modifies anything.
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.
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.
Command
Show model-routing stats - dispatches and real token volume kept off the session model. Args - --days N (window size, default 7), --ago M (shift window M days back), --session (only sessions on that model, e.g. fable).
Hook
Runs when a session starts on startup, executing update-check.mjs via node (2 commands). From AqueGen/model-routing.
Hook
Runs after a tool call finishes for Agent and Task tool calls, executing dispatch-counter.mjs via node. From AqueGen/model-routing.
Skill Claude CodeCodex
Route work to the cheapest model tier that holds quality. Use when deciding which model or agent should handle a task, when the user asks about token economy / cost optimization, or when dispatching implementation, review, or test-run work to subagents.
At most 3 mods per repository are shown here — the rest are on their repository pages: