Agentic Reviewer — Data & AI agent for Claude Code
Independent code reviewer for LLM and agent code.
How to install Agentic Reviewer
Installs to ~/.claude/agents/sktjpg-fde-poc-helper-agentic-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/sktjpg/fde-poc-helper/HEAD/.claude/agents/agentic-reviewer.md -o ~/.claude/agents/sktjpg-fde-poc-helper-agentic-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Agentic Reviewer does
name: agentic-reviewer description: "Independent code reviewer for LLM and agent code. Use after implementing a feature, or when asked to review (\"revisa\"), to find real defects - correctness bugs, unbounded loops, LLM failure modes, prompt injection paths, unvalidated tool input or output, missing error handling, missing tests. Read-only; reports findings, does not fix." tools: Read, Grep, Glob, Bash model: opus
You review a change in an agentic Python backend for an engineer working
Alternatives in Data & AI
- Svelte Correctness Review — Reviews a feature segment in any SvelteKit app (apps/moderator, apps/auth, apps/creator-studio) for correctnes 7.2k ★
- LLM AI Hunter — LLM and Agentic AI vulnerability specialist 812 ★
- Multi Agent Systems Architect Agent — Systems architect specializing in the design, coordination, and governance of multi-agent AI pipelines — cover 669 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kimchi Reviewer
Code reviewer for kimchi-claude. Use after a change is made (e.g. by kimchi-implementer) to find real correctn
Efcore Perf Reviewer
Read-only Entity Framework Core performance review — N+1 query patterns, per-row database round trips inside l
Data Integrity Review
Reviews a diff for data loss/corruption and functional correctness defects — wrong business logic, unsafe tran
Gsd Domain Researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domai
Gsd Eval Planner
Designs a structured evaluation strategy for an AI phase. Identifies critical failure modes, selects eval dime
Ferrox Domain Researcher
Researches the business domain and real-world application context of the AI system being built. Surfaces domai
Related Skills
Pre Commit Review
Independent QA review of a working-tree diff before commit. Spawns a read-only reviewer agent to find correctn
Claude Failures
Documented failure modes from working with Claude Code. Post-mortems of real incidents where the AI agent assu
Review AI Agent Surface
Audit the AI and agent attack surface: prompt injection, tool-permission scope, unbounded agent loops, and uns