Code Guardian — Data & AI agent for Claude Code
Reviews code against 12 professional standards: Clean Code, code-as-prose, SOLID, defensive programming, concurrency, error handling, the testing pyramid, API design, database patterns, observability.
How to install Code Guardian
Installs to ~/.claude/agents/sharang-gupta-thg-ai-coding-workflow-kit-code-guardian.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sharang-gupta-thg/ai-coding-workflow-kit/HEAD/agents/code-guardian.md -o ~/.claude/agents/sharang-gupta-thg-ai-coding-workflow-kit-code-guardian.md Restart Claude Code, or start a new session, for it to be picked up.
What Code Guardian does
name: code-guardian description: "Reviews code against 12 professional standards: Clean Code, code-as-prose, SOLID, defensive programming, concurrency, error handling, the testing pyramid, API design, database patterns, observability, code-review practice and refactoring. Use before a PR (full audit of a branch vs its base), mid-work (one function or file), or before writing code (where should this logic live?). Read-only: it reports findings ranked by severity and leaves the fixes to you."
Alternatives in Data & AI
- Presenter Agent — Creates presenter objects using SimpleDelegator for clean view formatting and display logic 652 ★
- Kiro Steering — agent-style v0.4.2 — literature-backed technical-prose writing rules for AI agents 650 ★
- Temporal Expert — Use this agent for Output.ai workflow abstractions, designing activity boundaries, implementing error handling 434 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Agent Reliability Reviewer
Use this agent to make an AI agent production-ready — reviewing its loops, cost controls, error handling, tool
Detailed Designer
Staff engineer for low-level design. Use proactively to turn an approved HLD into an implementable LLD — modul
Solid Skills
AI agent skill for writing senior-engineer quality code through SOLID principles, TDD, and clean architecture.
Review AI Newcomer
Reviews plans and specs from the perspective of a developer who is competent with software but new to AI-assis
Ops Monitor
Production observability expert. Use when designing monitoring, setting Sentry alerts, establishing error budg
LLM Expert
Use this agent for AI SDK integration, LLM provider configuration, prompt template management, error handling
Related Skills
Go Review
Comprehensive Go code review for idiomatic patterns, concurrency safety, error handling, and security. Invokes
Kotlin Coroutine Exception Handling
Agent skill for exception handling in Kotlin coroutines & Flow — structured concurrency, CancellationException
Sanyuan Skills
Expert code review skill: SOLID, security, performance, error handling, boundary conditions.