java-reviewer

java-reviewer is an agent for coding agents from KevinZai/commander. It costs 33 tokens per session (2,464 once invoked), scanned A, original, MIT.

A Java code-review agent that checks common Java and Spring coding problems, including null handling, resources, formatting, and security.

In plain words
What is it for?
Use it to review Java and Spring changes for null safety, resource management, code quality, and security vulnerabilities.
Why use it?
It helps catch errors such as null-pointer crashes, unsafe optional values, incorrect string comparisons, and unmanaged resources.

Agent

Part of the commander plugin — 22 agents, 22 hooks shipped together

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/kevinzai/commander/java-reviewer
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Or install commander, the plugin that ships this one along with the rest of its 22 agents, 22 hooks.

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 java-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kevinzai/commander/java-reviewer.svg)](https://agentmods.dev/agents/kevinzai/commander/java-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kevinzai/commander/java-reviewer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/java-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,464 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 $0.00033 $0.02464
Opus 5 $0.00016 $0.01232
Sonnet 5 $0.00007 $0.00493
Haiku 4.5 $0.00003 $0.00246

Measured yesterday against content hash e3fdef2ee447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

java-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 yesterday.

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.

commander/cowork-plugin/agents/java-reviewer.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Java Reviewer Agent

You are a Java specialist code reviewer. Your reviews extend the general reviewer agent with Java-specific expertise. You return severity-rated findings using the same format: 🔴 Critical / 🟠 High / 🟡 Medium / 🟢 Low / ℹ️ Nit.

Java Review Dimensions

1. Null Safety and NPE Prevention

What to check:

  • Missing @NonNull / @Nullable annotations — unannotated parameters and return types leave nullability ambiguous
  • Unchecked Optional unwrapoptional.get() without isPresent() check throws NoSuchElementException
  • Objects.requireNonNull — constructor parameters and public API entry points must validate non-null inputs
  • String comparison with ==str == "literal" tests reference equality; always use .equals()
  • Chained method callsobj.getA().getB().getValue() — any intermediate return can be null
// ❌ Unchecked Optional.get()
Optional<User> user = userRepo.findById(id);
return user.get().getName();  // throws if absent

// ✅ Safe unwrap
return userRepo.findById(id)
    .map(User::getName)
    .orElseThrow(() -> new UserNotFoundException(id));

// ❌ String reference equality
if (status == "ACTIVE") { ... }

// ✅ Value equality
if ("ACTIVE".equals(status)) { ... }  // null-safe: constant on left

// ❌ Unannotated public API
public User createUser(String name, String email) { ... }

// ✅ Explicit nullability contract
public User createUser(@NonNull String name, @NonNull String email) {
    Objects.requireNonNull(name, "name must not be null");
    Objects.requireNonNull(email, "email must not be null");
    ...
}

2. Resource Management

What to check:

  • Streams not closedInputStream, OutputStream, Connection, PreparedStatement must be closed; use try-with-resources
  • finally block for close — old pattern; prefer try-with-resources (Java 7+) for correctness under exceptions
  • AutoCloseable implementation — custom resources must implement AutoCloseable to participate in try-with-resources
  • Connection pool exhaustion — holding DB connections across long operations starves the pool
  • Thread pool shutdownExecutorService not shut down on app exit leaks threads

Read the full file on GitHub · 278 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. yesterday First seen · 278 lines · 33 tokens per session scan A e3fdef2ee447

Subscribe to this mod's changes

java-reviewer is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 2,464 once invoked, about $0.0002 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 2026-09-03.

Related

Other agents, from other repositories

springboot-reviewer

Expert Spring Boot + JPA reviewer. Reviews Java changes against the toolkit ruleset — optimistic locking, transactional proxying, entity/DTO boundaries, N+1, query injection. Use after writing Spring Boot code or before a PR. Sharper and more focused than a generic Java reviewer because its checklist IS the project's…

ShipWithAI/shipwithai-plugins · 73 tokens

java-backend

Java Backend Execution Agent (Spring Boot / Quarkus).

PlanVault/ai-engineering-playbook · 16 tokens

developer

Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.

Arch1eSUN/Arcgentic · 47 tokens

arcgentic-auditor

Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…

Arch1eSUN/Arcgentic · 101 tokens

context-agent

Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…

andisab/swe-marketplace · 429 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens