Borrowing it
Nothing to install: this file belongs to aave/aave-v4-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aave/aave-v4-sdk/main/.claude/agents/reviewer.mdgit clone --depth 1 https://github.com/aave/aave-v4-sdkWrote 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.
[](https://agentmods.dev/agents/aave/aave-v4-sdk/reviewer)<a href="https://agentmods.dev/agents/aave/aave-v4-sdk/reviewer"><img src="https://agentmods.dev/badge/agents/aave/aave-v4-sdk/reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00395 | $0.01132 |
| Opus 5.5 | $0.00158 | $0.00453 |
| Sonnet 5.5 | $0.00079 | $0.00226 |
| Haiku 4.5 | $0.00040 | $0.00113 |
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 2mo 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.
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?
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.
- 2mo ago First seen · 84 lines · 395 tokens per session scan A 9f46d247d5ae
reviewer is an agent published in the GitHub repository aave/aave-v4-sdk (26 stars, last pushed 8d ago), licensed MIT. It adds 395 tokens to every session and 1,132 once invoked, about $0.0016 per session on Opus 5.5. 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…