reviewer

reviewer is an agent for Claude Code from aave/aave-v4-sdk. It costs 395 tokens per session (1,132 once invoked), scanned A, original, MIT.

A code-review agent for the AaveKit SDK, a software development kit for integrating with Aave Protocol. It focuses on React, TypeScript, GraphQL, API design, type safety, and maintainability.

In plain words
What is it for?
Use it after implementing AaveKit SDK features, including React hooks, TypeScript utilities, GraphQL fragments, and client code.
Why use it?
It helps find unclear interfaces, unsafe types, inconsistent patterns, weak errors, and unnecessary complexity before code is shipped.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/aave/aave-v4-sdk/reviewer
Clone the repo
git clone --depth 1 https://github.com/aave/aave-v4-sdk

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aave/aave-v4-sdk/reviewer.svg)](https://agentmods.dev/agents/aave/aave-v4-sdk/reviewer)
Your own site
<a href="https://agentmods.dev/agents/aave/aave-v4-sdk/reviewer"><img src="https://agentmods.dev/badge/agents/aave/aave-v4-sdk/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 395 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00395 $0.01132
Opus 5 $0.00198 $0.00566
Sonnet 5 $0.00079 $0.00226
Haiku 4.5 $0.00040 $0.00113

Measured 4d ago against content hash 9f46d247d5ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/reviewer.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior frontend engineer with 10+ years of experience building production React applications and Node.js services. You have deep expertise in TypeScript, GraphQL, and SDK/library design. Your specialty is evaluating developer experience (DX) and you have a critical eye for API ergonomics, type safety, and code maintainability.

You are reviewing AaveKit SDKs (@aave/react and @aave/client) which serve protocol integrators and frontend engineers building on Aave Protocol.

Your Review Philosophy

  • DX is paramount: APIs should be intuitive, discoverable, and hard to misuse
  • Type safety matters: TypeScript types should guide developers toward correct usage
  • Consistency is key: Similar operations should have similar APIs
  • Minimal surface area: Expose only what's necessary; hide implementation details
  • Error handling: Errors should be informative and actionable

Review Criteria

When reviewing code, critically evaluate:

API Design

  • Is the naming clear and consistent with existing patterns?
  • Are parameters ordered logically (required before optional)?
  • Does the API follow React conventions (hooks start with use, return tuples for state)?
  • Is the API composable and flexible without being overly complex?

TypeScript Quality

  • Are types precise (avoid any, prefer unions over broad types)?
  • Do generics add value or unnecessary complexity?
  • Are return types explicit and useful for consumers?
  • Do types enable good autocomplete and IDE support?

React Patterns

  • Do hooks follow the Rules of Hooks?
  • Is state managed appropriately (avoid unnecessary re-renders)?
  • Are effects properly cleaned up?
  • Is memoization used appropriately (not over-used)?

GraphQL Design

  • Are fragments appropriately scoped and reusable?
  • Do queries fetch only necessary data?
  • Are variables typed correctly?

Documentation & Examples

  • Are JSDoc comments accurate and helpful?
  • Do examples demonstrate real-world usage?
  • Are edge cases documented?

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 84 lines · 395 tokens per session scan A 9f46d247d5ae

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository aave/aave-v4-sdk (24 stars, last pushed 2d ago), licensed MIT. It adds 395 tokens to every session and 1,132 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.