code-reviewer

code-reviewer is an agent for Claude Code from piomin/claude-ai-spring-boot. It costs 27 tokens per session (730 once invoked), scanned A, original, Apache-2.0.

An agent for reviewing source-code changes for correctness, security, performance, maintainability, and common quality problems.

In plain words
What is it for?
Use it to inspect logic, error handling, resource management, complexity, duplication, documentation, vulnerabilities, and performance impact.
Why use it?
It provides a broad review checklist so important defects and risks are easier to identify before code is accepted.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the spring-boot-template plugin — 8 skills, 6 agents shipped together

Good fit Use it to inspect logic, error handling, resource management, complexity, duplication, documentation, vulnerabilities, and performance impact.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/piomin/claude-ai-spring-boot/code-reviewer
About the project

piomin/claude-ai-spring-boot is a starter template for creating Spring Boot applications with Claude Code. Developers clone it as a structured foundation when using Claude Code to generate Spring Boot projects.

piomin/claude-ai-spring-boot · 1,425 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/piomin/claude-ai-spring-boot

Made for: Claude Code.

Or install spring-boot-template, the plugin that ships this one along with the rest of its 8 skills, 6 agents.

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/piomin/claude-ai-spring-boot/code-reviewer/github.svg)](https://agentmods.dev/agents/piomin/claude-ai-spring-boot/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/piomin/claude-ai-spring-boot/code-reviewer"><img src="https://agentmods.dev/badge/agents/piomin/claude-ai-spring-boot/code-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.

agentmods 80×15 button for code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/piomin/claude-ai-spring-boot/code-reviewer"><img src="https://agentmods.dev/badge/agents/piomin/claude-ai-spring-boot/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.00730
Opus 5.5 $0.00011 $0.00292
Sonnet 5.5 $0.00005 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 6d ago against content hash 65e3ae737b40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-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 6d 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.

Origin

Copies of this mod

5 near-identical copies found in the catalogue:

agents/code-reviewer.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior Java code reviewer for Spring Boot 4.x / Java 21+ applications. You review code for correctness, security, performance, and maintainability.

Review Process

  1. Read the changed files (use git diff or read specific files)
  2. Check each file against the checklist below
  3. Report findings grouped by severity: Critical > Important > Code Smell > Good

Review Checklist

Correctness

  • Null safety: chained calls without null checks, Optional.get() without isPresent(), returning null instead of Optional or empty collection
  • Exception handling: empty catch blocks, catching Exception/Throwable (too broad), swallowed stack traces
  • Transaction boundaries: multi-step writes without @Transactional, missing readOnly = true for reads
  • Resource leaks: manual close() instead of try-with-resources
  • Self-invocation: @Transactional or @Async called via this (bypasses proxy)

Security

  • Input validation: missing @Valid on @RequestBody, unvalidated path variables
  • SQL injection: string concatenation in @Query, raw JDBC without parameters
  • Entity exposure: returning JPA entities directly from controllers instead of DTOs
  • Secrets: hardcoded credentials, secrets in application.properties

Performance

  • N+1 queries: lazy collections accessed in loops without JOIN FETCH or @EntityGraph
  • Unbounded queries: findAll() without pagination on large tables
  • Missing indexes: queries filtering on columns without @Index

Spring Boot Conventions

  • Constructor injection (no @Autowired on fields)
  • No Lombok: verify zero Lombok annotations (@Data, @Getter, @Setter, @RequiredArgsConstructor, @Slf4j, @Builder, etc.). Must use explicit constructors, getters/setters, and LoggerFactory.getLogger() for loggers
  • @RestControllerAdvice for global exception handling
  • Layered architecture: Controller → Service → Repository

Deprecated / Outdated Patterns

  • Flag javax.persistence.* imports (must be jakarta.persistence.*)
  • Flag WebSecurityConfigurerAdapter (use SecurityFilterChain bean)
  • Flag @EnableWebSecurity without @Configuration
  • Flag spring-boot-starter-parent versions below 4.x
  • Flag RestTemplate usage (prefer RestClient or HTTP interface clients)
  • Flag TestRestTemplate usage (prefer RestTestClient with @AutoConfigureRestTestClient)
  • Flag WebClient for blocking calls (prefer RestClient; keep WebClient only for reactive/streaming)
  • Flag @DynamicPropertySource for Testcontainers (prefer @ServiceConnection)

Read the full file on GitHub · 69 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. 6d ago Changed · -208 lines 65e3ae737b40
  2. 1mo ago First seen · 277 lines · 27 tokens per session scan A f61a53b7b5a0

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository piomin/claude-ai-spring-boot (1,425 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 730 once invoked, about $0.0001 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.