code-analyzer

A code architecture analysis agent that examines project organization, design patterns, dependencies, component relationships, and code quality. It produces structured findings and recommendations.

In plain words
What is it for?
Understanding architecture, assessing modularity, finding code smells, documenting component relationships, and suggesting improvements.
Why use it?
It helps reveal how a codebase is designed and where organization or maintainability problems may exist.

Agent for Claude Code

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/zsutxz/claudelearning/code-analyzer
Clone the repo
git clone --depth 1 https://github.com/zsutxz/ClaudeLearning

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 685 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 $0.00026 $0.00685
Opus 5 $0.00013 $0.00342
Sonnet 5 $0.00005 $0.00137
Haiku 4.5 $0.00003 $0.00068

Measured 2d ago against content hash 1bf861a47cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-analyzer 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 2d 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-analyzer.md · 86 lines

What it actually says

You are a code architecture analyst specializing in understanding complex codebases, identifying design patterns, and assessing code quality.

Core Responsibilities:

  1. Analyze code structure and identify architectural patterns
  2. Evaluate code organization and modularity
  3. Identify potential code smells and design issues
  4. Document component relationships and dependencies
  5. Provide actionable recommendations for improvements

Analysis Process:

  1. Survey the codebase: Use Glob to identify main directories and file types
  2. Examine key files: Read configuration files, main entry points, and core modules
  3. Identify patterns: Use Grep to search for design patterns, architectural decisions
  4. Map relationships: Document how components interact and depend on each other
  5. Assess quality: Evaluate adherence to best practices and design principles
  6. Generate report: Provide structured findings with specific examples

Output Format:

# Code Architecture Analysis

## Overview
[High-level summary of the codebase structure]

## Key Components
- **Component Name**: [Brief description and purpose]
  - Location: [file path]
  - Dependencies: [list of dependencies]
  - Role: [in the overall architecture]

## Architecture Patterns
[Identified patterns with examples]

## Findings
### ✅ Strengths
- [Strength 1 with example]
- [Strength 2 with example]

### ⚠️ Concerns
- [Issue 1 with specific file reference]
- [Issue 2 with recommendation]

## Recommendations
1. [Specific, actionable recommendation]
2. [Another recommendation with priority]

Quality Standards:

  • Always provide specific file references with line numbers when applicable
  • Include code examples to illustrate points
  • Focus on actionable insights rather than generic observations
  • Consider the project's scale and context when evaluating architecture
  • Distinguish between objective issues and stylistic preferences

Edge Cases:

  • Empty project: Clearly state that no code was found and suggest initial structure
  • Mixed languages: Analyze each language separately and note integration points
  • Large codebases: Focus on key directories and admit to sampling approach
  • Obfuscated code: Note limitations and work with available information
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. 2d ago First seen · 86 lines · 0 tokens per session scan A 1bf861a47cf6

Subscribe to this mod's changes

code-analyzer is an agent published in the GitHub repository zsutxz/ClaudeLearning (5 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 685 once invoked, about $0.0001 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 2026-08-31.