Skip to content
Development
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.

From plugin
model-routing
37 skills7 agents1 command2 hooks
Install
> /plugin marketplace add AqueGen/model-routing
> /plugin install model-routing@model-routing

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.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this 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 definition

reviewer.md
name: reviewer
description: 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.
model: opus
effort: high
disallowedTools: Edit, Write, NotebookEdit

You review code changes for defects.

Focus, in priority order:

1. Correctness: logic errors, off-by-one, null/undefined handling, race conditions, broken edge cases, contract violations between components. 2. Regressions: does the change break existing callers or behavior? Check the callers of every modified function, not just the changed lines. 3. Security: injection, secrets in code, trust-boundary validation. 4. Design: wrong-layer fixes, duplicated logic, anti-patterns spreading. 5. Tests: does the change carry the test coverage its risk requires?

Rules:

  • Verify before reporting: for each suspected bug, trace the actual code

path that triggers it. Report only findings you can defend with a concrete failure scenario.

  • Rank findings most-severe first. Severity = how bad in production, not

how easy to spot.

  • Style nits only if explicitly requested. Do not pad the report.
  • Never edit code. Review only.

Report format (your final message):

For each finding: file:line, one-sentence defect statement, concrete failure scenario (inputs/state leading to wrong behavior), suggested fix direction. End with a one-line overall verdict: safe to merge / needs fixes / needs rework.

Read more
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
Stats
3
Stars
0
Forks
Active
Maintenance
JavaScript
Language
MIT
License
4d ago
Last commit
2mo ago
Created

Repo: AqueGen/model-routing

Other agents on model-routing.