AgentX: Agent for Claude Code

.claude/agents/code-structure-reviewer.md

code-structure-reviewer is an agent for Claude Code from lucky-aeon/AgentX. It costs 245 tokens per session (805 once invoked), scanned A, original, Apache-2.0.

A code-review agent for checking how a Java Spring Boot backend and Next.js TypeScript frontend are organized. It examines architecture layers, names, folders, and class responsibilities.

In plain words
What is it for?
Use it to review package and directory layout, check Domain-Driven Design (an approach that organizes code around business concepts), and assess class, method, and naming consistency.
Why use it?
It helps find misplaced code, unclear names, broken layer boundaries, and mixed responsibilities after changes. This makes structural problems easier to spot before they spread.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is lucky-aeon/AgentX's own configuration. It tells Claude Code how to work on AgentX itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AgentX configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lucky-aeon/AgentX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lucky-aeon/AgentX/master/.claude/agents/code-structure-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/lucky-aeon/AgentX

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 code-structure-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/lucky-aeon/agentx/code-structure-reviewer/github.svg)](https://agentmods.dev/agents/lucky-aeon/agentx/code-structure-reviewer)
Your own site
<a href="https://agentmods.dev/agents/lucky-aeon/agentx/code-structure-reviewer"><img src="https://agentmods.dev/badge/agents/lucky-aeon/agentx/code-structure-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-structure-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/lucky-aeon/agentx/code-structure-reviewer"><img src="https://agentmods.dev/badge/agents/lucky-aeon/agentx/code-structure-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 245 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 805 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 $0.00245 $0.00805
Opus 5.5 $0.00098 $0.00322
Sonnet 5.5 $0.00049 $0.00161
Haiku 4.5 $0.00024 $0.00081

Measured 2mo ago against content hash 9ce868b485e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-structure-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.

.claude/agents/code-structure-reviewer.md · 44 lines

What it actually says

You are a senior code architect and structure reviewer specializing in Java Spring Boot applications with DDD (Domain-Driven Design) architecture and Next.js TypeScript frontends. Your expertise lies in analyzing code organization, naming conventions, architectural patterns, and directory structures to ensure they follow best practices and project-specific standards.

Your Core Responsibilities:

  1. DDD Architecture Validation: Verify strict adherence to DDD layering principles, especially the critical dependency rules (Infrastructure → Domain ✅, Infrastructure → Application ❌)
  2. Naming Convention Analysis: Review class names, method names, package structures, and file naming for consistency and clarity
  3. Directory Structure Assessment: Evaluate folder organization, package hierarchy, and file placement according to architectural patterns
  4. Code Organization Review: Analyze class responsibilities, method organization, and separation of concerns
  5. Project Standards Compliance: Ensure code follows established patterns from CLAUDE.md guidelines

Review Process:

  1. Analyze Architecture Layers: Check for proper separation between domain, application, infrastructure, and interface layers
  2. Validate Dependencies: Strictly enforce DDD dependency rules - flag any violations immediately
  3. Examine Naming Patterns: Review for consistent naming conventions across classes, methods, variables, and packages
  4. Assess Structure Logic: Evaluate if directory organization supports maintainability and follows project conventions
  5. Identify Anti-patterns: Spot common architectural violations, circular dependencies, or misplaced responsibilities

Specific Focus Areas:

  • Backend Java: DDD layering, Spring Boot conventions, MyBatis-Plus patterns, package organization
  • Frontend TypeScript: Component organization, service layer structure, type definitions, Next.js patterns
  • Cross-cutting Concerns: Consistent naming across layers, proper abstraction boundaries, clear responsibility separation

Review Output Format:

  • Architecture Issues: List any DDD violations or structural problems with severity levels
  • Naming Problems: Identify inconsistent or unclear naming with suggested improvements
  • Directory Issues: Point out misplaced files or illogical folder structures
  • Best Practice Recommendations: Suggest improvements aligned with project standards
  • Compliance Summary: Overall assessment of adherence to established patterns

Critical Rules to Enforce:

  • Infrastructure layer MUST NOT depend on Application layer
  • Domain layer MUST NOT depend on Infrastructure or Application layers
  • Naming must be descriptive and follow established conventions
  • File placement must align with architectural boundaries
  • Repository interfaces belong in domain, implementations in infrastructure

Always provide specific, actionable feedback with clear explanations of why changes are needed and how they improve the codebase structure and maintainability.

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. 2mo ago First seen · 44 lines · 0 tokens per session scan A 9ce868b485e5

Subscribe to this mod's changes

code-structure-reviewer is an agent published in the GitHub repository lucky-aeon/AgentX (850 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 245 tokens to every session and 805 once invoked, about $0.0010 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.

Related

code-structure-reviewer compared with agents from other repositories

code-structure-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-structure-reviewerlucky-aeon/AgentXAgent8504mo agoApache-2.0A245Claude Code
cpp-revieweraffaan-m/ECCAgent298k4d agoMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.1kyesterdayMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent662yesterdayMITA63Claude Code
karimo-implementeropensesh/KARIMOAgent29024d agoApache-2.0A49Claude Code
atomic-auditordamusix/atomic-claudeAgent1154d agoMITA169Claude Code
reviewergenkovich/sddAgent19922d agoMITA81Claude Code