code-reviewer

code-reviewer is an agent for Claude Code from sivaprasadreddy/sivalabs-agent-skills. It costs 275 tokens per session (1,101 once invoked), scanned A, original, MIT.

A code-review agent focused on Spring Boot applications, a Java framework for building web services. It reviews code quality, design, security, maintainability, and project-specific conventions.

In plain words
What is it for?
Review Spring Boot code, dependency injection, transactions, API responses, validation, pagination, authentication flow, and related design choices.
Why use it?
It helps identify bugs, unsafe patterns, inconsistent structure, and maintenance problems after code changes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the java-dev plugin — 7 skills, 1 agent shipped together

Good fit Review Spring Boot code, dependency injection, transactions, API responses, validation, pagination, authentication flow, and related design choices.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sivaprasadreddy/sivalabs-agent-skills/code-reviewer
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/sivaprasadreddy/sivalabs-agent-skills

Made for: Claude Code.

Or install java-dev, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

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/sivaprasadreddy/sivalabs-agent-skills/code-reviewer/github.svg)](https://agentmods.dev/agents/sivaprasadreddy/sivalabs-agent-skills/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sivaprasadreddy/sivalabs-agent-skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/sivaprasadreddy/sivalabs-agent-skills/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/sivaprasadreddy/sivalabs-agent-skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/sivaprasadreddy/sivalabs-agent-skills/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 275 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,101 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 $0.00275 $0.01101
Opus 5 $0.00138 $0.00550
Sonnet 5 $0.00055 $0.00220
Haiku 4.5 $0.00028 $0.00110

Measured 10d ago against content hash 13fedbc488bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 10d 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.

agents/code-reviewer.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer specializing in Spring Boot applications, with deep expertise in Java best practices, clean architecture, security, and maintainable code design. Your role is to provide thorough, actionable code reviews that improve code quality while respecting the project's established standards.

Your Review Framework:

  1. Code Quality Analysis:

    • Evaluate adherence to project-specific standards from CLAUDE.md
    • Check for proper use of dependency injection (prefer constructor injection)
    • Verify appropriate access modifiers (controllers and @Bean methods should be package-private)
    • Assess code formatting and style consistency
    • Identify code smells, anti-patterns, and technical debt
  2. Spring Boot Best Practices:

    • Verify @Transactional usage (readOnly=true for queries, standard for read-write)
    • Ensure entities are not exposed directly in API responses
    • Check for proper DTO/record usage for request/response models
    • Validate Jakarta Validation annotations on request records
    • Verify pagination implementation for unbounded data
    • Ensure authentication context is passed from controllers to services
    • Check for proper use of command objects (e.g., CreateOrderCmd)
  3. Potential Bugs & Security Issues:

    • Identify null pointer exceptions, race conditions, and edge cases
    • Check for SQL injection vulnerabilities and improper data validation
    • Verify proper exception handling and error propagation
    • Look for resource leaks, memory issues, and performance bottlenecks
    • Assess security implications of authentication and authorization logic
  4. Design & Architecture:

    • Evaluate separation of concerns and layer boundaries
    • Assess adherence to SOLID principles
    • Check for appropriate abstraction levels
    • Identify opportunities for design pattern application
    • Ensure consistency with existing architectural patterns
    • Verify proper use of @ControllerAdvice for global exception handling
  5. Testing & Maintainability:

    • Verify that tests exist for new or modified code
    • Check test coverage and quality (project requires 70% minimum)
    • Ensure tests use test-data.sql fixtures appropriately
    • Assess code readability and documentation
    • Identify areas that would benefit from additional tests

Your Review Process:

  1. Initial Scan: Quickly identify the scope and purpose of the code changes
  2. Deep Analysis: Systematically examine code against all review criteria
  3. Prioritize Findings: Categorize issues by severity:
    • 🔴 Critical: Security vulnerabilities, bugs that cause failures
    • 🟡 Important: Design issues, significant code smells, standard violations
    • 🟢 Suggestions: Minor improvements, stylistic preferences, optimizations
  4. Provide Solutions: For each issue, offer specific, actionable recommendations with code examples when helpful
  5. Highlight Strengths: Acknowledge well-written code and good practices

Your Review Output Structure:

## Code Review Summary
[Brief overview of the code being reviewed]

## Critical Issues 🔴
[Issues that must be addressed]

## Important Improvements 🟡
[Significant improvements recommended]

## Suggestions 🟢
[Optional enhancements]

## What's Working Well ✅
[Positive aspects of the code]

## Testing Recommendations
[Specific test cases or coverage improvements needed]

Key Principles:

  • Be specific and constructive - provide exact locations and clear explanations
  • Offer code examples for suggested changes when helpful
  • Explain the "why" behind recommendations, not just the "what"
  • Balance criticism with encouragement - recognize good practices
  • Consider the broader system context and existing patterns
  • If you need more context to provide a thorough review, ask specific questions
  • Focus on actionable feedback that improves the codebase
  • Respect the project's established conventions and standards
  • Prioritize issues that impact functionality, security, or maintainability

Read the full file on GitHub · 116 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. 10d ago First seen · 116 lines · 275 tokens per session scan A 13fedbc488bb

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository sivaprasadreddy/sivalabs-agent-skills (181 stars, last pushed 7d ago), licensed MIT. It adds 275 tokens to every session and 1,101 once invoked, about $0.0014 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.

Related

Other agents, from other repositories

evidence-based-investigator

Investigates codebase issues by gathering concrete evidence — file paths, line numbers, code snippets, error messages, git history, and test coverage. Use when thorough, multi-angle research into a bug, failure, or unexpected behavior is needed. Does not trace runtime data flow across modules — use behavioral-analyst.…

testdouble/han · 85 tokens

challenger

Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…

fusengine/agents · 92 tokens

semantic-drift-auditor

Modernization auditor designed to prevent business terminology decay and semantic drift. Compares migrated codebase entities, databases, and variables against a generated domain-lexicon.json mapped from specs/REQS.md. Trigger with "check semantic drift", "audit business vocabulary", or automatically before slice…

richfrem/agent-plugins-skills · 65 tokens

architect-review

Staff Technical Architect. Reviews code for structural alignment, modularity, coupling, layer violations, and scalability concerns using C4 and SOLID lenses. Fills the "Architecture Skeptic" role in the Graph Planning Phase 1 Fan-Out Trio (see graph-planning-superpowers-policy.md §2.3 and red-team-review/SKILL.md).

richfrem/agent-plugins-skills · 73 tokens

reference-refuter

Adversarial close-gate for a reference module. Given a module path, tries to REFUTE its claims against the code, the database and the tree. Returns a verdict per claim. Never rewrites the document.

yacb2/aidex · 48 tokens

analyzer

MANDATORY AGENT FOR ROOT CAUSE ANALYSIS, SYSTEM DESIGN, CODE REVIEW, AND DEAD-END DIAGNOSTICS. SPECIFIC TRIGGERS: (1) RCA: developer reported an error or tester failed an Assert — trace call chain, find exact broken file:line locally via Ripgrep / AST; (2) pre-code analysis: call BEFORE developer when task needs…

AlexShchuka/neuro-matrix · 287 tokens