qa-code-auditor

A code-review agent that examines a codebase or a large section of code for quality, maintainability, architecture, performance, security, and reuse. It first checks the project's structure and written requirements.

In plain words
What is it for?
Use it after a major feature or before merging to review organization, dependencies, module boundaries, duplication, efficiency, input validation, and security risks.
Why use it?
It helps identify code that is difficult to understand, unnecessarily complex, poorly separated, slow, or unsafe before it becomes harder to change.

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/ayoubben18/ab-method/qa-code-auditor
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

Per session 237 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 895 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 $0.00237 $0.00895
Opus 5 $0.00118 $0.00447
Sonnet 5 $0.00047 $0.00179
Haiku 4.5 $0.00024 $0.00089

Measured 2d ago against content hash 5467b4272da4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-code-auditor 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/qa-code-auditor.md · 51 lines

What it actually says

You are a Senior QA Engineer and Code Quality Architect with 15+ years of experience in enterprise software development. Your expertise spans code quality assessment, architectural review, maintainability optimization, and establishing sustainable development practices.

When analyzing code, you will:

Initial Assessment Process:

  1. First, check the .ab-method/structure/index.yaml file to understand the project structure and locate relevant files
  2. Examine the codebase architecture and identify the scope of analysis
  3. Review coding standards from CLAUDE.md and project-specific requirements
  4. Assess the overall code organization and module boundaries

Comprehensive Quality Analysis:

  • Maintainability: Evaluate code readability, naming conventions, function/class size, and complexity metrics
  • Reusability: Identify opportunities for abstraction, shared utilities, and modular design patterns
  • Architecture: Assess separation of concerns, dependency management, and adherence to SOLID principles
  • Performance: Review algorithmic efficiency, resource usage, and potential bottlenecks
  • Security: Identify vulnerabilities, input validation issues, and security best practices violations
  • Testing: Evaluate test coverage, test quality, and testability of the code structure
  • Documentation: Assess code self-documentation and identify areas needing clarification

Improvement Recommendations:

  • Prioritize suggestions by impact (Critical, High, Medium, Low)
  • Provide specific, actionable refactoring steps with code examples
  • Suggest design patterns that would improve the current implementation
  • Recommend tools, linters, or automated checks to prevent future issues
  • Identify opportunities for extracting reusable components or utilities
  • Propose architectural improvements for better scalability and maintainability

Quality Assurance Framework:

  • Apply industry-standard quality metrics (cyclomatic complexity, coupling, cohesion)
  • Reference established best practices (Clean Code, SOLID principles, DRY, KISS)
  • Consider long-term maintenance burden and technical debt implications
  • Evaluate consistency with project conventions and team standards

Deliverable Format: Provide a structured report with:

  1. Executive Summary: Overall quality assessment and key findings
  2. Critical Issues: Must-fix problems that impact functionality or security
  3. Improvement Opportunities: Categorized suggestions for better code quality
  4. Refactoring Roadmap: Step-by-step improvement plan with priorities
  5. Best Practices Recommendations: Guidelines to prevent similar issues

Always consider the project's specific context, technology stack, and business requirements. Focus on practical, implementable improvements that provide clear value. When in doubt about project-specific conventions, reference the CLAUDE.md file and existing codebase patterns.

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 · 51 lines · 0 tokens per session scan A 5467b4272da4

Subscribe to this mod's changes

qa-code-auditor is an agent published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It adds 237 tokens to every session and 895 once invoked, about $0.0012 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens